Wan 3.0 Image to Video: Image-to-Video
Animate a source image into video with synchronized audio using Wan 3.0. Optional end-frame guidance, selectable resolution and duration. Try free.
Animate a source image into video with synchronized audio using Wan 3.0. Optional end-frame guidance, selectable resolution and duration. Try free.
About this model
Wan 3.0 Image to Video animates a source image using a motion prompt, producing a video with synchronized audio in one asynchronous Muapi call. Supply an optional last_image to guide how the shot should end, and choose 480p, 720p, or 1080p output, five aspect ratios, and a duration from 2 to 30 seconds. A thinking_mode flag helps the model reason through complex motion prompts, and audio generation can be disabled for a silent clip. For generating a scene from a text prompt with no source image, see Wan 3.0 Text to Video; for guiding a shot with multiple reference images, video, and audio, see Wan 3.0 Reference to Video. For the higher-fidelity Prime tier, see Wan 3.0 Prime Image to Video. For a bolder, higher-contrast take on the same request shape, see Wan 3.0 Spicy Image to Video.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | From $0.10 per generation (720p, 2s) up to $6.00 (1080p, 30s) | Pay-per-generation, priced by resolution and duration, no subscription required. |
| Fal.ai | Not available | Wan 3.0 is not listed on Fal.ai at this time. |
| Replicate | Not available | Wan 3.0 is not listed on Replicate at this time. |
Pay-per-generation, priced by resolution and duration, no subscription required.
Wan 3.0 is not listed on Fal.ai at this time.
Wan 3.0 is not listed on Replicate at this time.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Describe the motion and scene you want to create. | The camera slowly pushes in as a breeze moves through the subject's hair. |
| Image URL | string | Source image to animate. | undefined |
| Last Frame Image URL | string | Optional end-frame image to guide how the video should end. | undefined |
| Resolution | Enum (3 options) | Output video resolution. | 720p |
| Aspect Ratio | Enum (6 options) | Output video frame dimensions. | 16:9 |
| Duration | integer | Video length in seconds. | 5 |
| Thinking Mode | boolean | Enable deep-thinking mode for complex prompts. | false |
| Enable Audio | boolean | Include a generated audio track with the video. | true |
| Seed | integer | Random seed for reproducibility. Use -1 for a random seed. | -1 |
Describe the motion and scene you want to create.
The camera slowly pushes in as a breeze moves through the subject's hair.Source image to animate.
undefinedOptional end-frame image to guide how the video should end.
undefinedOutput video resolution.
720pOutput video frame dimensions.
16:9Video length in seconds.
5Enable deep-thinking mode for complex prompts.
falseInclude a generated audio track with the video.
trueRandom seed for reproducibility. Use -1 for a random seed.
-1Developer documentation
Provide the source image: Upload or link the starting frame with image_url.
Describe the motion: Use prompt to describe the camera movement and action you want.
Optionally guide the ending: Pass last_image to steer the video toward a specific end frame.
Set the output shape: Choose resolution (480p, 720p, 1080p), aspect_ratio, and duration (2-30 seconds), and toggle enable_audio or thinking_mode as needed.
Submit and poll: Send the request with your Muapi API key, store the returned request_id, then poll the prediction result endpoint or supply a webhook_url.
curl -X POST https://api.muapi.ai/api/v1/wan3.0-image-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The camera slowly pushes in as a breeze moves through the subject'\''s hair.",
"image_url": "https://example.com/portrait.jpg",
"resolution": "720p",
"duration": 5
}'
Frequently asked
It animates a source image into a video with synchronized audio, guided by a motion prompt and an optional end-frame image.
Send `prompt` describing the motion and `image_url` pointing to the source image. Local images can be uploaded through Muapi's upload endpoint first.
It's an optional end-frame image that guides how the generated video should conclude.
480p, 720p, or 1080p resolution, five aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4), and a duration of 2 to 30 seconds.
Yes, by default. Set `enable_audio` to `false` for a silent video.
Pricing scales with resolution and duration, and the completed task response includes the exact charge for that generation.