Wan 3.0 Spicy Reference to Video: AI Image-to-Video Generator
Generate bold, high-contrast video guided by reference images, video, and audio with Wan 3.0 Spicy. Keep characters and style consistent. Pay per generation.
Generate bold, high-contrast video guided by reference images, video, and audio with Wan 3.0 Spicy. Keep characters and style consistent. Pay per generation.
About this model
Wan 3.0 Spicy Reference to Video generates a bolder, higher-contrast, more dramatic video guided by a text prompt plus up to 10 reference images, 5 reference videos, and 5 reference audios, letting you keep characters, style, and sound consistent across a high-energy generated scene. It shares the exact request and result contract of the standard Wan 3.0 Reference to Video endpoint — reference media identified by array order, 480p/720p/1080p resolution, five aspect ratios, and a duration from 2 to 30 seconds — while tuning generation toward punchier motion. For a plain Spicy text-to-video generation with no reference media, see Wan 3.0 Spicy Text to Video; for animating a single source image, see Wan 3.0 Spicy Image to Video.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.055 – $6.60 per generation | Priced by resolution and duration (2-30s); a 10% premium over standard Wan 3.0 Reference to Video for the bolder Spicy styling. |
| Fal.ai | Not available | No comparable Wan 3.0 Spicy endpoint is listed. |
| Replicate | Not available | No comparable Wan 3.0 Spicy endpoint is listed. |
Priced by resolution and duration (2-30s); a 10% premium over standard Wan 3.0 Reference to Video for the bolder Spicy styling.
No comparable Wan 3.0 Spicy endpoint is listed.
No comparable Wan 3.0 Spicy endpoint is listed.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Describe the bold, high-motion video you want to create. Reference media are identified by their array order. | The two people from the reference images meet on the rainy street shown in the reference video. |
| Reference Image URLs | array | Up to 10 reference images for visual coherence guidance. | undefined |
| Reference Video URLs | array | Up to 5 reference video clips (MP4/MOV, 1-15s each); total reference + generated duration must not exceed 30s. | undefined |
| Reference Audio URLs | array | Up to 5 reference audio clips (total duration up to 15s) for soundtrack synchronization. | undefined |
| Resolution | Enum (3 options) | Output video resolution. | 720p |
| Aspect Ratio | Enum (5 options) | Output video frame dimensions. | 16:9 |
| Duration | integer | Video length in seconds. | 5 |
| Thinking Mode | boolean | Enable deep-thinking mode for complex scene understanding. | 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 bold, high-motion video you want to create. Reference media are identified by their array order.
The two people from the reference images meet on the rainy street shown in the reference video.Up to 10 reference images for visual coherence guidance.
undefinedUp to 5 reference video clips (MP4/MOV, 1-15s each); total reference + generated duration must not exceed 30s.
undefinedUp to 5 reference audio clips (total duration up to 15s) for soundtrack synchronization.
undefinedOutput video resolution.
720pOutput video frame dimensions.
16:9Video length in seconds.
5Enable deep-thinking mode for complex scene understanding.
falseInclude a generated audio track with the video.
trueRandom seed for reproducibility. Use -1 for a random seed.
-1Developer documentation
Write the prompt: describe the bold scene, referring to reference media by their array order (e.g. "the person from the first reference image").
Attach reference media: provide up to 10 URLs in images_list, up to 5 in videos_list, and up to 5 in audios_list.
Set the output shape: choose resolution (480p, 720p, 1080p), aspect_ratio, and duration (2-30 seconds, capped so reference-video duration plus output stays at or under 30 seconds).
Tune generation: enable thinking_mode for complex multi-reference scenes, and set enable_audio to false for a silent video.
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-spicy-reference-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The two people from the reference images meet on the rainy street shown in the reference video, with bold, dramatic motion.",
"images_list": ["https://example.com/ref1.jpg"],
"resolution": "720p",
"duration": 5
}'
Frequently asked
Spicy is Muapi's name for the bolder, higher-contrast, more dramatic-motion sibling of the standard Wan 3.0 endpoint. The request and result contract are identical — only the generated style is tuned to be punchier.
Up to 10 reference images, 5 reference videos, and 5 reference audios in a single request, identified in the prompt by their array order.
480p, 720p, or 1080p output at any duration from 2 to 30 seconds, in five aspect ratios: 16:9, 9:16, 1:1, 4:3, and 3:4.
Yes — the total reference-video duration plus the generated output duration must not exceed 30 seconds.
Sign up at muapi.ai, create an API key from your dashboard, and call POST /api/v1/wan3.0-spicy-reference-to-video immediately — no waitlist required.
Pricing is duration- and resolution-based, at a 10% premium over the standard Wan 3.0 Reference to Video rate. See the pricing table on this page for exact per-second rates.