Wan 2.2 Flash Image to Video

wan2.2-i2v-flash

wan2.2-i2v-flash Wan 2.2 Flash Image to Video Qwen video generation image to video first frame i2v flash

Wan 2.2 Flash Image to Video generates video from an input image, balancing speed with common quality controls.

Endpoints

POST /v1/queue/wan2.2-i2v-flash # Create task

GET /v1/queue/wan2.2-i2v-flash/requests/{request_id}/status # Check status

GET /v1/queue/wan2.2-i2v-flash/requests/{request_id}/response # Get result

PUT /v1/queue/wan2.2-i2v-flash/requests/{request_id}/cancel # Cancel task

Tip

Include the authentication header in each request: Authorization: Bearer YOUR_API_KEY.

Aspect ratio

Image-to-video output is scaled to the requested resolution tier while staying close to the input image aspect ratio. Portrait input images can return portrait output, such as a 720x1264, 5-second MP4 with resolution=720P.

Request parameters

curl --location "https://odirouter.ai/model/v1/queue/wan2.2-i2v-flash" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A red apple slowly rotating on a white table, clean studio lighting, static camera.",
    "img_url": "https://example.com/reference-image.webp",
    "duration": 5,
    "resolution": "720P",
    "prompt_extend": true,
    "watermark": false,
    "seed": 12345
  }'

prompt string required

Text prompt describing the expected elements and visual characteristics in the generated video. Chinese and English are supported. For wan2.2 series models, the length must not exceed 800 characters; extra content is automatically truncated.

img_url string required

First-frame image URL or Base64-encoded data.

Image formats: JPEG, JPG, PNG, BMP, WEBP. PNG images do not support transparent channels.

Image width and height: 360 - 2000 pixels.

File size: no more than 10MB.

duration int

For wan2.2-i2v-flash, duration is fixed at 5 seconds and cannot be changed.

Fixed value: 5

resolution string

Generated video resolution tier. The model scales to a similar total pixel count and tries to preserve an aspect ratio close to img_url.

Options: 480P, 720P

Default: 720P

prompt_extend bool

Whether to enable intelligent prompt rewriting. When enabled, a large model rewrites the input prompt, which can significantly improve short-prompt results but increases latency.

Options: true, false

Default: true

seed int

Random seed. If omitted, the system automatically generates a random seed. Fixing seed can improve reproducibility, but the same seed does not guarantee identical results every time.

Range: 0 - 2147483647

watermark bool

Whether to add a watermark in the lower-right corner of the video.

Options: false, true

Default: false

Response parameters

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://odirouter.ai/model/v1/queue/wan2.2-i2v-flash/requests/mmsu_01hxyz.../response",
  "status_url": "https://odirouter.ai/model/v1/queue/wan2.2-i2v-flash/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://odirouter.ai/model/v1/queue/wan2.2-i2v-flash/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
request_id	string	Task ID used for all follow-up operations.
response_url	string	URL to fetch the final result.
status_url	string	URL to query task status.
cancel_url	string	URL to cancel the task.
queue_position	int	Current queue position.

Follow-up operations

Check status

Get result

Cancel task

Error handling