Skip to content
youbot
Docs menu
APIFile UploadAccount & Common

Video models

Wan 2.7 Video

On this page

Wan 2.7 Video — high-quality AI video generation.

modelIdwan-2-7-text-to-video, wan-2-7-image-to-video, wan-2-7-r2v, wan-2-7-videoedit
Modalityvideo
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Text To Videowan-2-7-text-to-videoPOST /api/v1/generateprompt
Image To Videowan-2-7-image-to-videoPOST /api/v1/generateprompt
Reference to Videowan-2-7-r2vPOST /api/v1/generateprompt
Video Editwan-2-7-videoeditPOST /api/v1/generatevideo_url
Poll task—GET /api/v1/task/{id}?model=wan-2-7-text-to-video—

Text To Video — wan-2-7-text-to-video

FieldTypeRequiredValues / example
promptstringYesThe positive prompt for the generation Max 5000 characters. (default: A sandcastle builds itself grain by grain on an empty beach in time-lapse. Audio: soft waves, distant seagulls.)
negative_promptstringNoThe negative prompt for the generation Max 500 characters.
audio_urlstringNoAudio URL for the generation (image URL)
resolutionstringNoThe resolution of output (options: 720p | 1080p) (default: 1080p)
ratiostringNoThe ratio of output (options: 16:9 | 9:16 | 1:1 | 4:3 | 3:4) (default: 16:9)
durationnumberNoTotal duration of output (range 2-15) (default: 5)
prompt_extendbooleanNoWether to enable the prompt optimizer (true/false) (default: true)
watermarkbooleanNoWether to enable the watermark (true/false) (default: false)
seednumberNoThe random seed to use for the generation.(>=0,<=2147483647) (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-text-to-video","input":{"prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","negative_prompt":"blurry, low quality, distorted, watermark, text","audio_url":"https://example.com/input.mp3","resolution":"720p","ratio":"16:9","duration":5,"prompt_extend":true,"watermark":false,"seed":0,"nsfw_checker":true}}'

Image To Video — wan-2-7-image-to-video

FieldTypeRequiredValues / example
promptstringYesThe positive prompt for the generation Max 5000 characters. (default: Animate the first frame: the manta ray glides forward with slow, graceful wing-beats, a gentle parallax through drifting plankton as shafts of sunlight sway across its broad back.)
negative_promptstringNoThe negative prompt for the generation Max 500 characters.
first_frame_urlstringNoThe first frame of output (image URL)
last_frame_urlstringNoThe last frame of output (image URL)
first_clip_urlstringNoAudio URL to guide generation (image URL)
driving_audio_urlstringNoAudio URL for the generation (image URL)
resolutionstringNoThe resolution of output (options: 720p | 1080p) (default: 1080p)
durationnumberNoTotal duration of output (range 2-15) (default: 5)
prompt_extendbooleanNoWether to enable the prompt optimizer (true/false) (default: true)
watermarkbooleanNoWether to enable the watermark (true/false) (default: false)
seednumberNoThe random seed to use for the generation(>=0,<=2147483647) (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-image-to-video","input":{"prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","negative_prompt":"blurry, low quality, distorted, watermark, text","first_frame_url":"https://example.com/input.jpg","last_frame_url":"https://example.com/input.jpg","first_clip_url":"https://example.com/input.mp4","driving_audio_url":"https://example.com/input.mp3","resolution":"720p","duration":5,"prompt_extend":true,"watermark":false,"seed":0,"nsfw_checker":true}}'

Reference to Video — wan-2-7-r2v

FieldTypeRequiredValues / example
promptstringYesThe positive prompt for the generation Max 5000 characters. (default: Bring the reference scene to life: drift the camera slowly forward as low fog creeps across an alpine wildflower meadow, blossoms swaying in a faint breeze and shafts of dawn light gradually brightening the frame.)
negative_promptstringNoThe negative prompt for the generation Max 500 characters.
reference_imagestring[]NoAn array of reference image URLs. At least one of the following must be provided: a reference image or a reference video; the total number of images and videos cannot exceed 5. (image URL)
reference_videostring[]NoAn array of reference video URLs. At least one of the reference images and reference videos must be passed in; the total number of images and videos cannot exceed 5 (image URL)
first_framestringNoThe URL of the first frame image; a maximum of one image can be passed. The aspect_ratio will be automatically ignored after passing the URL, and an approximate aspect ratio video will be generated based on the aspect ratio of the first frame image. (image URL)
reference_voicestringNoAudio URL. Used to specify the timbre of the main character in the reference material. (image URL)
resolutionstringNoThe resolution of output (options: 720p | 1080p) (default: 1080p)
aspect_ratiostringNoOutput Video Aspect Ratio. If first_frame is not passed: the video will be generated according to the specified aspect_ratio. First_frame has been passed in: Aspect_ratio is automatically ignored, and an approximate aspect ratio video is generated based on the aspect ratio of the first frame. (options: 16:9 | 9:16 | 1:1 | 4:3 | 3:4) (default: 16:9)
durationnumberNoOutput video duration, in seconds. Values ​​must be integers between 2 and 10, with a default value of 5 (range 2-10) (default: 9)
prompt_extendbooleanNoEnable intelligent prompt rewriting. Enabling it uses a larger model to expand the input prompt, which works better for short prompts, but increases processing time (true/false) (default: true)
watermarkbooleanNoAdd a watermark. The watermark is located in the bottom right corner of the video, and the text is fixed as "AI generated". (true/false) (default: false)
seednumberNoThe random seed to use for the generation(>=0,<=2147483647) (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-r2v","input":{"prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","negative_prompt":"blurry, low quality, distorted, watermark, text","reference_image":["https://example.com/input.jpg"],"reference_video":["https://example.com/input.mp4"],"first_frame":"https://example.com/input.jpg","reference_voice":"https://example.com/input.mp3","resolution":"720p","aspect_ratio":"16:9","duration":5,"prompt_extend":true,"watermark":false,"seed":0,"nsfw_checker":true}}'

Video Edit — wan-2-7-videoedit

FieldTypeRequiredValues / example
video_urlstringYesThe source video to edit (image URL)
promptstringNoThe positive for the generation Max 5000 characters. (default: Restyle the clip into a neo-noir cityscape at dusk, deepening the shadows and adding warm sodium streetlights with drifting fog, while preserving the original camera motion and timing.)
reference_imagestringNoList of reference images for video editing (image URL)
negative_promptstringNoThe negative for the generation Max 500 characters.
resolutionstringNoOutput video resolution (options: 720p | 1080p) (default: 720p)
durationstringNoOutput video duration in seconds. Default 0 means using the full input video duration without truncation If a value is provided, the output is clipped from second 0 to the specified length Valid values are 0 or any integer in [2,10] (options: 0 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10) (default: 9)
aspect_ratiostringNoOutput video aspect ratio (options: 16:9 | 9:16 | 1:1 | 4:3 | 3:4) (default: 16:9)
audio_settingstringNoauto:The model intelligently determines whether to regenerate audio based on the prompt. origin:Force preservation of original audio from input video (options: auto | origin) (default: auto)
prompt_extendbooleanNoEnable intelligent prompt rewriting. Enabling it uses a larger model to expand the input prompt, which works better for short prompts, but increases processing time. (true/false) (default: true)
watermarkbooleanNoAdd a watermark. The watermark is located in the bottom right corner of the video, and the text is fixed as "AI generated". (true/false) (default: false)
seednumberNoRandom seed, range 0-2147483647. Automatically generated by the system if not transmitted. (default: 0)
nsfw_checkerbooleanNoA configurable parameter. Defaults to true in the Playground. (true/false) (default: true)
bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"wan-2-7-videoedit","input":{"video_url":"https://example.com/input.mp4","prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","reference_image":"https://example.com/input.jpg","negative_prompt":"blurry, low quality, distorted, watermark, text","resolution":"720p","duration":"0","aspect_ratio":"16:9","audio_setting":"auto","prompt_extend":true,"watermark":false,"seed":0,"nsfw_checker":true}}'
HappyHorse-1.0FLUX.2