Wan 2.7 - Reference to Video

Endpoint

POST /videos/generations

Full URL: https://modelfold.ai/v1/videos/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Input parameters for the reference-to-video task.

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	The model name used for generation. This field is required. This endpoint must use the wan/2-7-r2v model. Default："wan/2-7-r2v"。 Allowed values：wan/2-7-r2v。 Example：wan/2-7-r2v。
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. Text prompt. Required. Describes the desired elements and visual features in the generated video. Supports Chinese and English. Maximum length: 5000 characters. maxLength: 2000. Example：Image 1 is eating, while video 1 and image 2 are singing beside it.。
negative_prompt	string	No	Optional negative prompt describing what should not appear in the video. Supports Chinese and English. Maximum length: 500 characters. maxLength: 500. Example：low resolution, errors, worst quality, low quality, malformed, extra fingers, bad proportions。
reference_image	array<string>	No	Array of reference image URLs. At least one of reference_image or reference_video must be provided. The total number of images and videos cannot exceed 5. maxItems: 5.
reference_video	array<string>	No	Array of reference video URLs. At least one of reference_image or reference_video must be provided. The total number of images and videos cannot exceed 5. maxItems: 5.
first_frame	string	No	First frame image URL. At most one image can be provided. If supplied, aspect_ratio is ignored and the output uses a ratio close to the first frame image. Example：https://example.com/demo/first-frame.png。
reference_voice	string	No	Audio URL used to specify the voice timbre of the subject in the reference material. Rules: - If reference_video contains audio and reference_voice is not provided, the original video audio is used by default - If both reference_video and reference_voice are provided, reference_voice takes priority Audio limits: - Formats: wav, mp3 - Duration: 1 to 10 seconds - File size: up to 30MB Example：https://example.com/demo/reference-voice.mp3。
resolution	string	No	Output video resolution tier. Available values: 720p, 1080p. Default value: 1080p. Default："1080p"。 Allowed values：720p / 1080p。 Example：1080p。
aspect_ratio	string	No	Output video aspect ratio. Effective logic: - If first_frame is not provided: the video is generated using the specified aspect_ratio - If first_frame is provided: aspect_ratio is ignored and the output uses a ratio close to the first frame image Default："16:9"。 Allowed values：16:9 / 9:16 / 1:1 / 4:3 / 3:4。 Example：16:9。
duration	integer	No	Output video duration in seconds. Valid range is an integer from 2 to 10. Default value: 5. Default：5。 minimum: 2. maximum: 10. Example：5。
prompt_extend	boolean	No	Whether to enable prompt rewriting. When enabled, the model expands the input prompt. This usually works better for short prompts but increases processing time. Default：true。 Example：true。
watermark	boolean	No	Whether to add a watermark. The watermark is placed in the lower-right corner of the video with the fixed text "AI generated". Default：false。 Example：false。
seed	integer	No	Random seed. Range: 0-2147483647. If omitted, the system generates one automatically. minimum: 0. maximum: 2147483647. Example：0。
nsfw_checker	boolean	No	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Request Example

curl -X POST "https://modelfold.ai/v1/videos/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan/2-7-r2v",
  "prompt": "Image 1 is eating, while video 1 and image 2 are singing beside it.",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 5,
  "prompt_extend": true,
  "watermark": false
}'

{
  "model": "wan/2-7-r2v",
  "prompt": "Image 1 is eating, while video 1 and image 2 are singing beside it.",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 5,
  "prompt_extend": true,
  "watermark": false
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp4"
    }
  ],
  "usage": {}
}