Video models
Wan 2.5
Wan 2.5 — high-quality AI video generation.
| modelId | wan-2-5-image-to-video, wan-2-5-text-to-video |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Image To Video | wan-2-5-image-to-video | POST /api/v1/generate | prompt, image_url |
| Text To Video | wan-2-5-text-to-video | POST /api/v1/generate | prompt |
| Poll task | — | GET /api/v1/task/{id}?model=wan-2-5-image-to-video | — |
Image To Video — wan-2-5-image-to-video
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | The text prompt describing the desired video motion Max 800 characters. (default: Animate the still: the chef plates the final course, swirling a ribbon of sauce and setting a single herb leaf with tweezers, steam rising under warm pass lighting, a subtle push-in on the hands.) |
| image_url | string | Yes | URL of the image to use as the first frame. Must be publicly accessible (image URL) |
| duration | string | No | The duration of the generated video in seconds (options: 5 | 10) (default: 5) |
| resolution | string | No | Video resolution. Valid values: 720p, 1080p (options: 720p | 1080p) (default: 1080p) |
| negative_prompt | string | No | Negative prompt to describe content to avoid Max 500 characters. |
| enable_prompt_expansion | boolean | No | Whether to enable prompt rewriting using LLM (true/false) (default: true) |
| seed | number | No | Random seed for reproducibility. If None, a random seed is chosen |
| nsfw_checker | boolean | No | A 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-2-5-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.","image_url":"https://example.com/input.jpg","duration":"5","resolution":"720p","negative_prompt":"blurry, low quality, distorted, watermark, text","enable_prompt_expansion":true,"seed":1,"nsfw_checker":true}}'Text To Video — wan-2-5-text-to-video
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | The text prompt for video generation. Supports Chinese and English, max 800 characters. Max 800 characters. (default: A hot slice of pizza lifts away from the pan in a long stretch of melting cheese, flour dust drifting in the oven's amber glow as the camera tracks the rising slice in crisp slow motion.) |
| duration | string | No | The duration of the generated video in seconds (options: 5 | 10) (default: 5) |
| aspect_ratio | string | No | The aspect ratio of the generated video (options: 16:9 | 9:16 | 1:1) (default: 16:9) |
| resolution | string | No | Video resolution tier (options: 720p | 1080p) (default: 1080p) |
| negative_prompt | string | No | Negative prompt to describe content to avoid. Max 500 characters. Max 500 characters. |
| enable_prompt_expansion | boolean | No | Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. (true/false) (default: true) |
| seed | number | No | Random seed for reproducibility. If None, a random seed is chosen. |
| nsfw_checker | boolean | No | A 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-2-5-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.","duration":"5","aspect_ratio":"16:9","resolution":"720p","negative_prompt":"blurry, low quality, distorted, watermark, text","enable_prompt_expansion":true,"seed":1,"nsfw_checker":true}}'