{"data":[{"created":1787788800,"id":"gemini-omni-flash-1-1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 is Google's video model; this text-to-video variant turns prompts into 4- to 10-second clips at up to 4K. Sibling variants cover image-to-video, reference-to-video and video editing.","name":"Gemini Omni Flash 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1's image-to-video variant animates a starting image into a 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1 video model.","name":"Gemini Omni Flash 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 R2V combines several reference images of characters, objects or styles into one 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1.","name":"Gemini Omni Flash 1.1 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["360p","720p","1080p","4k"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 Edit rewrites an existing clip from a text instruction, keeping its length, at up to 4K. It's the video editing variant of Google's Gemini Omni Flash 1.1.","name":"Gemini Omni Flash 1.1 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 is ByteDance Seed's cinematic video model, with native audio and lip-sync in more than eight languages. This text-to-video variant generates 4- to 15-second clips at up to 4K.","name":"Seedance 2.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 4K, with optional synchronized dialogue and sound.","name":"Seedance 2.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 R2V builds 4- to 15-second clips at up to 4K from reference images, videos and audio, and can also edit or extend existing footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.0.","name":"Seedance 2.0 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0, generating 4- to 15-second clips at up to 720p from text, with optional native audio and lip-sync.","name":"Seedance 2.0 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional synchronized audio.","name":"Seedance 2.0 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast R2V is the reference-driven variant of Seedance 2.0 Fast, generating, editing or extending 4- to 15-second clips at up to 720p from reference images, videos and audio.","name":"Seedance 2.0 Fast R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini is ByteDance Seed's cost-effective Seedance 2.0 model for high-volume video creation. This text-to-video variant generates 4- to 15-second clips at up to 720p, with optional native audio.","name":"Seedance 2.0 Mini","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional native audio, for high-volume work.","name":"Seedance 2.0 Mini","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini R2V is the reference-driven variant of Seedance 2.0 Mini, building 4- to 15-second clips at up to 720p from reference images, videos and audio.","name":"Seedance 2.0 Mini R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 is the next generation of ByteDance Seed's cinematic video model, with native audio and stories of up to 30 seconds. This text-to-video variant generates 4- to 30-second clips at up to 4K.","name":"Seedance 2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5's image-to-video variant turns a starting image into a 4- to 30-second clip at up to 4K, with optional native audio.","name":"Seedance 2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 R2V builds 4- to 30-second clips at up to 4K from up to 30 reference images plus reference videos and audio, and can edit or extend footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.5.","name":"Seedance 2.5 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-edit-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["Auto"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Edit changes a 4- to 30-second source video by swapping subjects, objects or styles, while keeping its original motion, camera and length. Reference images are optional, and output is up to 4K.","name":"Seedance 2.5 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 is Alibaba's video model, generating 2- to 30-second clips at up to 1080p from text, with optional native audio.","name":"Wan 3.0","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p, with optional native audio.","name":"Wan 3.0","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Reference generates 2- to 30-second clips at up to 1080p from reference images, videos and audio, keeping subjects consistent at the pixel level.","name":"Wan 3.0 Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime is a high-speed version of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 1080p from text much faster, with optional native audio.","name":"Wan 3.0 Prime","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p.","name":"Wan 3.0 Prime","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Reference is the high-speed reference variant of Wan 3.0, building 2- to 30-second clips at up to 1080p from reference images, videos and audio with consistent subjects.","name":"Wan 3.0 Prime Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro is the highest-resolution tier of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 4K from text, with optional native audio.","name":"Wan 3.0 Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.","name":"Wan 3.0 Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro Reference builds 2- to 30-second clips at up to 4K from reference images, videos and audio, keeping subjects consistent at the pixel level.","name":"Wan 3.0 Pro Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro combines the speed of Wan 3.0 Prime with the 4K output of Wan 3.0 Pro, generating 2- to 30-second clips from text, with optional native audio.","name":"Wan 3.0 Prime Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.","name":"Wan 3.0 Prime Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro Reference is the fastest 4K reference variant of Wan 3.0, building 2- to 30-second clips from reference images, videos and audio with consistent subjects.","name":"Wan 3.0 Prime Pro Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":false,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations","featured"],"description":"Wan 2.7 is Alibaba's video model, served uncensored, for high-fidelity text-to-video in 5-, 10- or 15-second clips at up to 1080p. It can follow an audio track you provide.","name":"Wan 2.7","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":false,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7's image-to-video variant animates a starting image, or a first-and-last-frame pair, into an uncensored 5-, 10- or 15-second clip at up to 1080p. It can follow an audio track you provide.","name":"Wan 2.7","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":true,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source","venice_recommendations"],"description":"Wan 2.7 Reference generates uncensored 5- or 10-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.","name":"Wan 2.7 Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["uncensored","high_resolution","open_source","venice_recommendations"],"description":"Wan 2.7 Edit changes an existing video from text instructions, with an optional reference image, at up to 1080p. It's the uncensored editing variant of Alibaba's Wan 2.7.","name":"Wan 2.7 Edit","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1778284800,"id":"wan-2-7-enhanced-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p.","name":"Wan 2.7 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780444800,"id":"wan-2-7-enhanced-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p.","name":"Wan 2.7 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786665600,"id":"wan-2-2-enhanced-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["5s","8s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","open_source"],"description":"Wan 2.2 Enhanced is a version of Alibaba's Wan 2.2 for uncensored image-to-video, animating a starting image into a 5- or 8-second clip at up to 720p.","name":"Wan 2.2 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution"],"description":"HappyHorse 1.1 is Alibaba's video model, with synchronized native audio and multilingual lip-sync. This text-to-video variant generates 3- to 15-second clips at up to 1080p.","name":"HappyHorse 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.1's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio and multilingual lip-sync.","name":"HappyHorse 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":400},"model_sets":["high_resolution"],"description":"HappyHorse 1.1 Reference builds 3- to 15-second clips at up to 1080p from reference images, keeping characters consistent, with native audio and multilingual lip-sync.","name":"HappyHorse 1.1 Reference","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776988800,"id":"happyhorse-1-0-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","featured"],"description":"HappyHorse 1.0 is Alibaba's video model with native audio. This text-to-video variant generates high-fidelity 3- to 15-second clips at up to 1080p.","name":"HappyHorse 1.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777075200,"id":"happyhorse-1-0-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.0's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio.","name":"HappyHorse 1.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777248000,"id":"happyhorse-1-0-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":400},"model_sets":["high_resolution"],"description":"HappyHorse 1.0 Reference generates 3- to 15-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.","name":"HappyHorse 1.0 Reference","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777248000,"id":"happyhorse-1-0-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["Auto"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.0 Edit changes an existing video from text instructions, with optional reference images, at up to 1080p with native audio.","name":"HappyHorse 1.0 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1765843200,"id":"wan-2.6-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 is Alibaba's video model with audio support. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p, with optional audio, and can follow an audio track you provide.","name":"Wan 2.6","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1768824000,"id":"wan-2.6-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 Flash is a fast version of Alibaba's Wan 2.6 for image-to-video, animating a starting image into a 5-, 10- or 15-second clip at up to 1080p with native audio.","name":"Wan 2.6 Flash","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1765843200,"id":"wan-2.6-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 is Alibaba's video model with audio support. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p, with optional audio, and can follow an audio track you provide.","name":"Wan 2.6","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"wan-2.5-preview-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p","480p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source"],"description":"Wan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This image-to-video variant animates a starting image into a 5- or 10-second clip at up to 1080p with native audio.","name":"Wan 2.5 Preview","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"wan-2.5-preview-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p","480p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source"],"description":"Wan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This text-to-video variant generates 5- or 10-second clips at up to 1080p with native audio.","name":"Wan 2.5 Preview","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776038400,"id":"grok-imagine-text-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic"],"description":"Grok Imagine is xAI's video model, generating 1- to 15-second clips at up to 720p from text, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-image-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic"],"description":"Grok Imagine's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 720p, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-reference-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["photorealistic"],"description":"Grok Imagine R2V generates 1- to 10-second clips at up to 720p from several reference images, which you cite in the prompt as @Image1, @Image2 and so on.","name":"Grok Imagine R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-video-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["480p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","venice_recommendations"],"description":"Grok Imagine's video editing variant changes an existing clip from text instructions, in 5-, 10- or 15-second results at up to 720p, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780185600,"id":"grok-imagine-1-5-text-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution","venice_recommendations","featured"],"description":"Grok Imagine 1.5 is xAI's updated video model, generating 1- to 15-second clips at up to 1080p from text, with native audio.","name":"Grok Imagine 1.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780185600,"id":"grok-imagine-1-5-image-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution","venice_recommendations"],"description":"Grok Imagine 1.5's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.","name":"Grok Imagine 1.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785283200,"id":"grok-imagine-1-5-reference-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","venice_recommendations"],"description":"Grok Imagine 1.5 R2V generates 1- to 15-second clips at up to 720p from up to 7 reference images, with native audio.","name":"Grok Imagine 1.5 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1790726400,"id":"grok-imagine-1-5-lite-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution"],"description":"Grok Imagine 1.5 Lite is a quicker, more affordable version of xAI's Grok Imagine 1.5, generating 1- to 15-second clips at up to 1080p from text, with native audio.","name":"Grok Imagine 1.5 Lite","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1790726400,"id":"grok-imagine-1-5-lite-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution"],"description":"Grok Imagine 1.5 Lite's image-to-video variant quickly turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.","name":"Grok Imagine 1.5 Lite","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.","name":"LTX Video 2.3 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.","name":"LTX Video 2.3 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-full-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 4K, with optional audio.","name":"LTX Video 2.3 Full Quality","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-full-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This text-to-video variant generates 6-, 8- or 10-second clips at up to 4K, with optional audio.","name":"LTX Video 2.3 Full Quality","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","open_source"],"description":"LTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.","name":"LTX Video 2.5 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","open_source"],"description":"LTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.","name":"LTX Video 2.5 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16"],"resolutions":["720p","1080p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","open_source"],"description":"LTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 1080p, with optional audio.","name":"LTX Video 2.5 Pro","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","open_source"],"description":"LTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This text-to-video variant generates 6-, 8- or 10-second clips at up to 1080p, with optional audio.","name":"LTX Video 2.5 Pro","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"ovi-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","audio","open_source"],"description":"Ovi is Character.AI's open-weight audio-video model, based on Wan, that animates a starting image into a 5-second clip with native audio. It runs fast and is served uncensored.","name":"Ovi","modelSource":"https://huggingface.co/chetwinlow1/Ovi","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations","fast"],"description":"MiniMax H3 Max is a post-trained variant of MiniMax's H3 video model. This text-to-video variant generates 5- to 15-second clips at up to 1080p with native stereo audio.","name":"MiniMax H3 Max","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations","fast"],"description":"MiniMax H3 Max's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.","name":"MiniMax H3 Max","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1789171200,"id":"minimax-h3-max-multi-angle","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","high_resolution","long_duration","cinematic","audio","fast"],"description":"MiniMax H3 Max Multi-Angle moves a virtual camera around a single image, with precise control of orbit, elevation and distance, producing 5- to 15-second clips at up to 1080p with native audio.","name":"MiniMax H3 Max Multi-Angle","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-reference-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations"],"description":"MiniMax H3 Max R2V generates 5- to 15-second clips at up to 1080p from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.","name":"MiniMax H3 Max R2V","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1791331200,"id":"minimax-h3-max-recast","model_spec":{"privacy":"private","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["768P","1080P"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":2000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","high_resolution","long_duration","cinematic","photorealistic"],"description":"MiniMax H3 Max Recast replaces the people in a source video with people from reference photos, preserving the original motion, camera, cuts and soundtrack, at up to 1080p.","name":"MiniMax H3 Max Recast","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788307200,"id":"minimax-h3-max-turbo-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","fast"],"description":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, generating 5- to 15-second clips at up to 1080p from text with native stereo audio.","name":"MiniMax H3 Max Turbo","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788307200,"id":"minimax-h3-max-turbo-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","fast"],"description":"MiniMax H3 Max Turbo's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.","name":"MiniMax H3 Max Turbo","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1733186476,"id":"kling-2.6-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["5s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic"],"description":"Kling 2.6 Pro is Kling AI's full-quality video model with native audio generation. This text-to-video variant generates 5- or 10-second clips, with optional audio.","name":"Kling 2.6 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1733186476,"id":"kling-2.6-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic"],"description":"Kling 2.6 Pro's image-to-video variant animates a starting image into a 5- or 10-second clip, with optional native audio.","name":"Kling 2.6 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"kling-2.5-turbo-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["5s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","photorealistic"],"description":"Kling 2.5 Turbo Pro is Kling AI's full-quality Kling 2.5 video model, generating 5- or 10-second clips from text.","name":"Kling 2.5 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"kling-2.5-turbo-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","photorealistic"],"description":"Kling 2.5 Turbo Pro's image-to-video variant animates a starting image into a 5- or 10-second clip.","name":"Kling 2.5 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-v3-4k-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","ultra_high_resolution"],"description":"Kling V3 4K generates video at native 4K without upscaling, using Kling AI's V3 model. This text-to-video variant makes 3- to 15-second clips, with optional audio.","name":"Kling V3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-v3-4k-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","ultra_high_resolution"],"description":"Kling V3 4K R2V animates a start frame into native 4K video, using reference elements to keep characters and objects consistent, in 3- to 15-second clips with optional audio.","name":"Kling V3 4K R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K generates native 4K video with Kling AI's O3 model, tuned for stylized and anime looks. This text-to-video variant makes 3- to 15-second clips, with optional audio.","name":"Kling O3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K's image-to-video variant animates a starting image, with an optional end image, into native 4K stylized or anime motion, in 3- to 15-second clips.","name":"Kling O3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K R2V combines up to 7 character, object or style references into a single native 4K clip of 3 to 15 seconds, with optional audio.","name":"Kling O3 4K R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","venice_recommendations"],"description":"Kling O3 Pro is the premium tier of Kling AI's O3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling O3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","venice_recommendations"],"description":"Kling O3 Pro's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.","name":"Kling O3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1773014400,"id":"kling-o3-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Pro R2V turns images and elements into 3- to 15-second clips with stable character identity, using a frontal image and reference images for each element.","name":"Kling O3 Pro R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard is the balanced tier of Kling AI's O3 video model, trading some quality for speed. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling O3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.","name":"Kling O3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1773100800,"id":"kling-o3-standard-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard R2V turns images and elements into 3- to 15-second clips with stable character identity, at the Standard tier's balance of quality and speed.","name":"Kling O3 Standard R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1779667200,"id":"kling-v3-pro-motion-control","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":[],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["cinematic","photorealistic","long_duration"],"description":"Kling V3 Pro Motion Control transfers the movements in a reference video onto a character image, at Kling V3 Pro quality. The output follows the length of the source video.","name":"Kling V3 Pro Motion Control","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Pro is the enhanced-quality tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling V3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Pro's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.","name":"Kling V3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1779667200,"id":"kling-v3-standard-motion-control","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":[],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["cinematic","photorealistic","long_duration"],"description":"Kling V3 Standard Motion Control transfers the movements in a reference video onto a character image, a cost-effective option for portraits and simple animations. The output follows the length of the source video.","name":"Kling V3 Standard Motion Control","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Standard is the balanced tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling V3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Standard's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.","name":"Kling V3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Pro is a faster version of Kling V3 Pro, generating 3- to 15-second clips at 1080p from text, with multi-shot storyboards.","name":"Kling V3 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Pro's image-to-video variant animates a start frame into a 3- to 15-second clip at 1080p, with multi-shot storyboards.","name":"Kling V3 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Standard is a faster, cost-effective version of Kling V3, generating 3- to 15-second clips at 720p from text, with multi-shot storyboards.","name":"Kling V3 Turbo Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Standard's image-to-video variant animates a start frame into a 3- to 15-second clip at 720p, with multi-shot storyboards.","name":"Kling V3 Turbo Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","21:9"],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 is Kling AI's fourth-generation video model. This text-to-video variant generates 3- to 30-second clips at 720p or 1080p with native audio, and supports multi-shot prompts.","name":"Kling 4.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0's image-to-video variant animates a starting image, with optional end-frame control, into a 3- to 30-second clip at 720p or 1080p with native audio and multi-shot prompts.","name":"Kling 4.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16","1:1","21:9"],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 R2V generates 3- to 30-second clips at 720p or 1080p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame and multi-shot prompts.","name":"Kling 4.0 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","21:9"],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash is a faster version of Kling AI's Kling 4.0, generating 3- to 20-second clips at 720p from text with native audio.","name":"Kling 4.0 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash's image-to-video variant animates a start frame into a 3- to 20-second clip at 720p with native audio.","name":"Kling 4.0 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16","1:1","21:9"],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash R2V generates 3- to 20-second clips at 720p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame.","name":"Kling 4.0 Flash R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["720p"],"durations":["Auto"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash Edit changes a source video from a text instruction and up to 10 reference images, at 720p with native audio. The output follows the length of the source video.","name":"Kling 4.0 Flash Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-distilled-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.","name":"Longcat Distilled","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-distilled-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This text-to-video variant generates 5- to 30-second clips at 720p.","name":"Longcat Distilled","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.","name":"Longcat Full Quality","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This text-to-video variant generates 5- to 30-second clips at 720p.","name":"Longcat Full Quality","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Fast is a faster version of Google's Veo 3.1 video model. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.","name":"Veo 3.1 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Fast's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.","name":"Veo 3.1 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-full-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Full Quality runs Google's Veo 3.1 video model at full quality. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.","name":"Veo 3.1 Full Quality","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-full-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Full Quality's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.","name":"Veo 3.1 Full Quality","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash is Google's video model for 4- to 10-second clips from text prompts. Gemini Omni Flash 1.1 is its newer successor.","name":"Gemini Omni Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash's image-to-video variant animates a starting image into a 4- to 10-second clip, using Google's Gemini Omni Flash video model.","name":"Gemini Omni Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash R2V combines several reference images into one 4- to 10-second clip, using Google's Gemini Omni Flash video model.","name":"Gemini Omni Flash R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 is Black Forest Labs' video model with synchronized audio. This text-to-video variant generates 5- to 20-second clips at up to 4K.","name":"Flux 3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3's image-to-video variant animates a single still image into a 5- to 20-second clip at up to 4K, with synchronized audio.","name":"Flux 3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-first-last-frame-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 First Last Frame generates the transition between a start frame and an end frame, as a 5- to 20-second clip at up to 4K with synchronized audio.","name":"Flux 3 First Last Frame","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-extend-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 Extend continues an existing clip beyond its final frame, adding 5 to 20 seconds at up to 4K with synchronized audio.","name":"Flux 3 Extend","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792108800,"id":"flux-3-max-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["auto","21:9","2:1","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","1080p"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Flux 3 Max is Black Forest Labs' post-trained Flux 3 video model, built for high visual quality at high speed. This text-to-video variant generates 5- to 20-second clips at up to 1080p with synchronized audio.","name":"Flux 3 Max","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792108800,"id":"flux-3-max-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","2:1","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","1080p"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Flux 3 Max's image-to-video variant animates a still image, with an optional end frame, into a 5- to 20-second clip at up to 1080p with synchronized audio.","name":"Flux 3 Max","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6 is PixVerse's video model. This text-to-video variant generates 5- or 8-second clips at up to 1080p, with optional audio.","name":"PixVerse v5.6","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6's image-to-video variant animates a starting image into a 5- or 8-second clip at up to 1080p, with optional audio.","name":"PixVerse v5.6","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-transition","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6 Transition creates a smooth transition between a start image and an end image, as a 5- or 8-second clip at up to 1080p, with optional audio.","name":"PixVerse v5.6 Transition","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 is PixVerse's film-grade video model, generating 3- to 15-second clips at up to 1080p from text, with optional native audio.","name":"PixVerse C1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1's image-to-video variant animates a starting image into a cinematic 3- to 15-second clip at up to 1080p, with optional native audio.","name":"PixVerse C1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 R2V generates character-consistent 3- to 15-second clips at up to 1080p from reference images of subjects and backgrounds, with optional native audio.","name":"PixVerse C1 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-transition","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 Transition creates a seamless cinematic transition between a start image and an end image, as a 3- to 15-second clip at up to 1080p, with optional native audio.","name":"PixVerse C1 Transition","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769817600,"id":"vidu-q3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","4:3","3:4","1:1"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","12s","14s","16s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","long_duration","cinematic","venice_recommendations"],"description":"Vidu Q3 is Vidu's video model. This text-to-video variant generates 3- to 16-second clips at up to 1080p, with optional audio.","name":"Vidu Q3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769817600,"id":"vidu-q3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","12s","14s","16s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","long_duration","cinematic","venice_recommendations"],"description":"Vidu Q3's image-to-video variant animates a starting image into a 3- to 16-second clip at up to 1080p, with optional audio.","name":"Vidu Q3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775952000,"id":"runway-gen4-5","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["cinematic","photorealistic"],"description":"Runway Gen-4.5 is Runway's video model. This image-to-video variant animates a starting image into a 2- to 10-second clip.","name":"Runway Gen-4.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775952000,"id":"runway-gen4-5-text","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["cinematic","photorealistic"],"description":"Runway Gen-4.5's text-to-video variant generates 2- to 10-second clips from prompts of up to 1,000 characters, using Runway's Gen-4.5 video model.","name":"Runway Gen-4.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769040000,"id":"runway-gen4-turbo","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["fast","cinematic","photorealistic","fast"],"description":"Runway Gen-4 Turbo is a faster version of Runway's Gen-4 video model, animating a starting image into a 2- to 10-second clip.","name":"Runway Gen-4 Turbo","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775174400,"id":"topaz-video-upscale","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["2x","4x"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["high_resolution","ultra_high_resolution"],"description":"Topaz Video Upscale uses Topaz Labs' upscaling to enlarge an existing video 2x or 4x while restoring detail. The output keeps the source video's length.","name":"Topaz Video Upscale","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785888000,"id":"minimax-h3-enhanced-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 Enhanced is a version of MiniMax's H3 (Hailuo 3) tuned for uncensored output. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.","name":"MiniMax H3 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785888000,"id":"minimax-h3-enhanced-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 R2V Enhanced generates uncensored 5- to 15-second clips at up to 2K from reference images and audio, with native audio.","name":"MiniMax H3 R2V Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3, also called Hailuo 3, is MiniMax's video model. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.","name":"MiniMax H3","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 2K with native audio.","name":"MiniMax H3","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 R2V generates 5- to 15-second clips at up to 2K from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.","name":"MiniMax H3 R2V","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"}],"object":"list","type":"video"}