Skip to main content
POST
/
v3
/
async
/
wan2.7-i2v
Wan 2.7 Image-to-Video
curl --request POST \
  --url https://api.novita.ai/v3/async/wan2.7-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "prompt": "<string>",
  "duration": 123,
  "image_url": "<string>",
  "watermark": true,
  "resolution": "<string>",
  "prompt_extend": true,
  "first_clip_url": "<string>",
  "last_frame_url": "<string>",
  "negative_prompt": "<string>",
  "driving_audio_url": "<string>"
}
'
{
  "task_id": "<string>"
}
Wan 2.7 Image-to-Video model with multimodal input support (text/image/audio/video). Capable of first-frame-to-video, first+last-frame-to-video, and video continuation. Supports 720P and 1080P resolutions, duration 2~15 seconds, billed per second. Output includes audio by default.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
seed
integer
Random seed for improving reproducibility. Range: [0, 2147483647].Value range: [0, 2147483647]
​
prompt
string
Text prompt describing desired video content. Supports Chinese and English, max 5000 characters.Length limit: 0 - 5000
​
duration
integer
default:5
Video duration in seconds, billed per second. Range: [2, 15] integer.Value range: [2, 15]
​
image_url
string
required
First frame image URL. Supported formats: JPEG, JPG, PNG (no transparency), BMP, WEBP. Resolution: width and height in [240, 8000] pixels, aspect ratio 1:8~8:1, max 20MB. Mutually exclusive with first_clip_url, at least one must be provided.
​
watermark
boolean
default:false
Add watermark to the output video (bottom-right corner).
​
resolution
string
default:"1080P"
Output video resolution tier, affects pricing. Video aspect ratio matches input media.Optional values: 720P, 1080P
​
prompt_extend
boolean
default:true
Enable intelligent prompt rewriting using LLM. Improves generation quality for short prompts but increases processing time.
​
first_clip_url
string
First video clip URL for video continuation. The model extends the video based on its content. Supported formats: mp4, mov. Duration: 210s, resolution: width and height in [240, 4096] pixels, aspect ratio 1:88:1, max 100MB. Mutually exclusive with image_url.
​
last_frame_url
string
Last frame image URL. Combined with first frame to generate first+last frame video. Same format restrictions as first frame.
​
negative_prompt
string
Negative prompt describing undesired content in the video. Supports Chinese and English, max 500 characters.Length limit: 0 - 500
​
driving_audio_url
string
Driving audio URL. When provided, the model uses it as the driving source for video generation (e.g., lip sync, motion beats). When omitted, the model auto-generates matching background music or sound effects. Supported formats: wav, mp3. Duration: 2~30s, max 15MB.

​
Response

​
task_id
string
Use the task_id to request the Task Result API to retrieve the generated outputs.