Wan 3.0 Prime Reference-to-Video
Wan 3.0 Prime Reference-to-Video is Alibaba's flagship controllable video generation model built for precise reference-conditioned visual synthesis. Powered by an upgraded spatio-temporal decoupling architecture and multi-reference feature fusion, it preserves character identity, garment textures, ambient lighting, and complex camera trajectories across extended sequences while generating native 4K high-frame-rate video. Operating with strict temporal consistency and fluid motion dynamics, Wan 3.0 Prime drives e-commerce video production, cinematic pre-visualization, digital human animation, and commercial advertising pipelines.
Wan 3.0 Prime Reference-to-Video
Wan 3.0 Prime Reference-to-Video is an ultra-fast, high-quality AI reference-to-video model from Alibaba’s Tongyi Wanxiang series. Combining the ultra-fast rendering capabilities of the Prime architecture with Wan 3.0’s multimodal foundation, the model supports single-image first-frame guidance and smooth transitions between first and last frames. It can directly generate 1080p HD videos up to 30 seconds long. The model natively integrates joint audio-video generation, including ambient sound effects and multilingual character lip synchronization. In addition to significantly reducing video rendering wait times, it provides highly accurate motion physics simulation, camera movement control, and subject consistency. It is widely applicable to dynamic e-commerce product presentations, film and television visual effects, rapid short-drama iteration, and commercial advertising production.
Base URL
https://api.icreat.aiAuthentication
All API requests require authentication using an API key. You can obtain an API key from the console.
export ICREAT_API_KEY="your-api-key-here"HTTP Request Headers
import os
API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer " + API_KEY,
}Keep Your API Key Secure
Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy.
Code Examples
Image and video generation uses a two-step async flow: submit a task to get task_id, then poll via query task result; the response includes status and result ([] while processing; on SUCCEEDED, result holds resources and costUSD is present). The examples below use the same task_id across both steps.
1. Submit a Task
Send a generation request to the submission endpoint.
2. Query Task Result (Poll)
Use the task_id from submit to poll progress (repeat until terminal). The response includes status and result: result is [] while processing; on SUCCEEDED, result holds resources and costUSD is included; FAILED means the task failed.
Input Parameters
Submit Task — Input Parameters
The following parameters are accepted in the task submission request body.
Total: 2; Required: 2; Optional: 0
The input content for the generation task.
Generation parameters.
Query Task Result — Input
Total: 1 Required: 1 Optional: 0
The task ID returned from the submit endpoint.
Output Parameters
Submit Task — Output Parameters
Total: 1
The task ID returned by the task submission endpoint.
Query Task Result — Output
Total: variable
Current task status. result is usually [] until success; on SUCCEEDED, result holds resources and costUSD is present.
Generated resources. Empty array while processing or on failure; array of objects on success.
Task cost in USD. Present only when status is SUCCEEDED.
LLM Prompt
The Markdown below is an LLM-friendly prompt you can paste into AI assistants (e.g. Cursor, ChatGPT) to help them understand this model's API, call flow, and key parameters. Use Copy for AI or copy from the code block below.
# aliyun/wan3-0-prime/reference-to-video
> Wan 3.0 Prime Reference-to-Video is an ultra-fast, high-quality AI reference-to-video model from Alibaba’s Tongyi Wanxiang series.
## Overview
Use the iCreat two-step async task API: submit a generation request, then poll the query task result endpoint; on success read resources from `result` (includes `costUSD`).
## API Info
- **Base URL**：`https://api.icreat.ai`
- **Submit endpoint (POST)**：`/v1/task/submit/aliyun/wan3-0-prime/reference-to-video`
- **Query result endpoint (POST)**：`/v1/task/result`
- **Model ID**：`aliyun/wan3-0-prime/reference-to-video`
- **Auth**：`Authorization: Bearer ${ICREAT_API_KEY}`
## Call Flow
1. **Submit**: POST submit path with body per Input Notes; response `{ "task_id": "..." }`
2. **Query result**: POST `/v1/task/result` with `{ "task_id": "..." }`; response includes `status` and `result` (`[]` while processing); on `SUCCEEDED`, `result` holds resources and `costUSD` is present; read `url` or `download_url` when `type` is `Video`
### Input Notes
- Top-level body: `input` (object) + `parameters` (object) as siblings
- `input.prompt` (required): A prompt describing the video to generate.
- `input.negative_prompt` (optional): A description of content that should not appear in the video.
- `input.media` (optional): A list of reference media used for reference-to-video generation.
- `parameters.resolution` (required): The video resolution.
- `parameters.ratio` (required): The video aspect ratio.
- `parameters.duration` (required): The video duration in seconds.
- `parameters.watermark` (optional): Whether to add a watermark.
### Output Notes
- Poll: read `status`; `result` is `[]` while processing
- Success: `result` is `[{ "type": "Video", "url": "...", "download_url": "..." }]` plus `costUSD`
## Notes
- Use the same `task_id` across both steps; `result` is `[]` while processing — keep polling
- `FAILED` is terminal — check request parameters or reference media
- `input` and `parameters` are sibling top-level fields; do not nest them