Wan-3.0 Reference-to-video
All-in-One Reference: keep subjects consistent from any mix of reference images, videos, and audio; pixel-level identity/voice/space alignment.
What it does
Wan-3.0 Reference-to-video, in practice.
Wan 3.0 Reference-to-Video is the "all-in-one reference" mode: give it any mix of reference images, videos, and audio, and it keeps those subjects, props, voices, and spatial relationships consistent throughout a new clip driven by your prompt. This is pixel-level identity preservation — not "close enough," but faithful replication of the reference details.
- Mix four modalities Combine reference images, reference videos, and reference audio in one request.
- Pixel-level consistency Characters, props, voices, and spatial relationships stay aligned across the whole clip.
- Multi-subject scenes Reference several subjects at once and direct them with your prompt.
- Native long-form + audio Up to 30 seconds with a synchronized audio track.
- Flexible aspect ratios adaptive, 16:9, 4:3, 1:1, 3:4, or 9:16.
Product photo workspace
This page is a model reference. The workspace supports white backgrounds, scene changes, packaging text edits and model try-on using Qwen Image Edit.
Parameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | The text prompt describing the scene and action for the referenced subjects (up to 20000 characters). | |
refers | All-in-One Reference materials. Each item requires a public URL and explicit media type. Image: jpeg/jpg/png/bmp/webp; video: mp4/mov; audio: wav/mp3. Reference mode is mutually exclusive with first/last-frame mode. | |
resolution | Output resolution. Native tiers: 480p, 720p, 1080p. ESR tiers: 720p-esr, 1080p-esr, 1440p-esr, 4k-esr. | 1080p 720p 480p 720p-esr 1080p-esr 1440p-esr 4k-esr |
duration | Video length in seconds (2-30). Pass -1 for smart-duration (the model picks the best length). | -1 2 3 4 5 6 7 8 9 10 11 12 |
ratio | The aspect ratio of the generated video. Use 'adaptive' to let the model choose from the references. | adaptive 16:9 4:3 1:1 3:4 9:16 |
audio | Whether the output video includes an audio track. Same price either way. | default True |
enable_thinking | Enable deep thinking mode. Required when providing a file or link input (document / webpage parsing). Not recommended when no file/link is provided. | default |
file | Optional document input to parse (requires enable_thinking). Public URL. Formats: docx, doc, xlsx, xls, pptx, ppt, pdf, txt, key, pages, numbers, md; <= 100MB, <= 50 pages. Mutually exclusive with 'link'. | |
link | Optional public webpage URL to parse (requires enable_thinking). Only pages that need no login. Mutually exclusive with 'file'. | |
seed | The random seed to use for the generation. -1 means a random seed will be used. |
Sample prompt
The prompt behind the sample.
Convert video to comic style
resolution: 1080Pduration: 5ratio: 9:16enable_thinking: Trueaudio: TrueFAQ
Short answers.
How much does Wan-3.0 Reference-to-video cost?
List price starts at $0.060 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $0.48. Per-use pricing, no subscription. Model prices are reference prices. The prompt workspace is free during the period shown on the homepage; no automatic charges.
What content policy applies to Wan-3.0 Reference-to-video?
Qwen's standard content policy, plus this site's commercial-use rules: product, catalog and marketing work. Uploads are processed for your request only and are not used for training.
What does Wan-3.0 Reference-to-video take as input?
It is a video-to-video model. All-in-One Reference: keep subjects consistent from any mix of reference images, videos, and audio; pixel-level identity/voice/space alignment.
How do I use Wan-3.0 Reference-to-video?
Upload the source clip and describe the change: restyle, extend, re-time, or replace the background. Source length and frame rate bound the output, so start from the cleanest version you have. Register or sign in to edit product photos with Qwen Image Edit. Other models on this page are catalog references.
Related