Wan-3.0 Image-to-video
Animate a first frame (optionally with a last frame) into a coherent clip, with native audio and smart-duration up to 30s.
What it does
Wan-3.0 Image-to-video, in practice.
Wan 3.0 Image-to-Video animates a still image into a coherent, hyper-realistic clip driven by your text prompt. Supply a first frame — and optionally a last frame — and the model renders the motion, camera work, and synchronized audio in between, up to 30 seconds.
- First-frame / first-and-last-frame Strict frame control: pin the opening (and optionally closing) frame of your clip.
- Native long-form generation Up to 30 seconds in a single pass.
- Smart duration Let the model pick the ideal length (`duration = -1`).
- Sound on by default Synchronized audio track; toggle off at no extra cost.
- Hyper-real rendering Film-grade texture, lighting, and lifelike movement.
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 motion / action for the video (up to 20000 characters). | |
image | First frame of the video (strict first-frame mode). Public URL. Formats: jpeg, jpg, png (no alpha), bmp, webp. Single edge 240-8000px, aspect ratio <= 8:1, <= 20MB. | |
last_image | Optional last frame of the video. When provided, the model interpolates from the first frame to this one. Same format limits as 'image'. | |
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 |
audio | Whether the output video includes an audio track. Same price either way. | default True |
seed | The random seed to use for the generation. -1 means a random seed will be used. |
Sample prompt
The prompt behind the sample.
The car slowly moved forward in the canyon.
resolution: 1080Pduration: 5audio: TrueFAQ
Short answers.
How much does Wan-3.0 Image-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 Image-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 Image-to-video take as input?
It is a image-to-video model. Animate a first frame (optionally with a last frame) into a coherent clip, with native audio and smart-duration up to 30s.
How do I use Wan-3.0 Image-to-video?
Supply the first frame and describe only the motion. The still is the contract: identity, wardrobe, light and framing stay, so keep the prompt about camera and movement, not about changing the subject. Aspect ratio should match the still. Register or sign in to edit product photos with Qwen Image Edit. Other models on this page are catalog references.
Compare
Head-to-head, with real specs and samples.
Related