Text-to-image
Create a new image from a descriptive prompt.
AvailableWan 3.0 · image and video generation
Wan 3.0 API
Use Wan 3.0 on Muapi for text-to-image, image editing, text-to-video, and image-to-video generation. All four workflows use the same asynchronous submit-and-poll pattern, so your application can keep one integration while switching between creative modes.
Wan 3.0 API is available on Muapi
Choose a model below, submit a generation request with your Muapi API key, and poll the returned request ID for the image or video URL.
Watch: Wan 3.0 API Tutorial
Wan 3.0 API capabilities
Muapi exposes the Wan 3.0 family through focused endpoints with simple request bodies and a consistent result format.
Instruction-based editing
Send a source image and describe the edit in plain language.
Text-to-video
Generate a video directly from a written scene or shot brief.
Image-to-video
Animate a supplied image with a focused motion prompt.
One API key
Use Muapi authentication, billing, and task responses across every mode.
Async generation
Submit a task, store its request ID, and poll for the completed output.
Wan 3.0 model pages
Choose the image or video workflow for your application.
T2IAvailable
Wan 3.0 Text to Image
Generate images from a natural-language prompt through Muapi's asynchronous API.
Text to ImageMuapi async API
Open model page →EDITAvailable
Wan 3.0 Image Edit
Apply an instruction prompt to a source image and receive the edited image URL.
Image to ImageMuapi async API
Open model page →T2VAvailable
Wan 3.0 Text to Video
Turn a written scene description into a generated video through one Muapi endpoint.
Text to VideoMuapi async API
Open model page →I2VAvailable
Wan 3.0 Image to Video
Animate a source image with a motion prompt while keeping the input image as the visual starting point.
Image to VideoMuapi async API
Open model page →SPICYAvailable
Wan 3.0 Spicy Text to Video
Use higher-energy text-to-video workflows with the Wan 3.0 Spicy variant.
Text to VideoMuapi async API
Open model page →SPICYAvailable
Wan 3.0 Spicy Image to Video
Use more expressive image animation workflows with the Wan 3.0 Spicy variant.
Image to VideoMuapi async API
Open model page →How the Wan 3.0 API works
- Send the prompt and, for edit or image-to-video modes, the source image URL.
- Receive a request ID immediately from the selected Wan endpoint.
- Poll the prediction result endpoint or provide a webhook for completion.
- Read the generated image or video URL from the completed response.
One Wan 3.0 integration
Wan 3.0 uses Muapi's shared authentication, task lifecycle, file upload, and billing infrastructure. Add Wan 3.0 beside other image and video models without maintaining a separate provider client.
Wan 3.0 API endpoints
Every Wan 3.0 request uses the same Muapi REST contract. Submit JSON with the x-api-key header, then poll the standard prediction endpoint.
Submit a generation task
curl -X POST https://api.muapi.ai/api/v1/wan3.0-text-to-image \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"An editorial product photograph on blue silk"}'Retrieve the completed result
curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \ -H "x-api-key: YOUR_API_KEY"
Use the returned `outputs` or media field for the final image or video URL.
Wan 3.0 API FAQ
What can I create with Wan 3.0?
Wan 3.0 provides text-to-image, instruction-based image editing, text-to-video, and image-to-video endpoints through Muapi.
How do I access Wan 3.0?
Create a Muapi API key, send it in the x-api-key header, and call the Wan 3.0 endpoint that matches your workflow.
Can I use a ComfyUI workflow?
Yes. The Wan 3.0 ComfyUI node pack provides API-key, generation, image-upload, polling, and media-saver nodes.
How are Wan 3.0 requests completed?
Generation is asynchronous. Store the request ID returned by the submit call, then poll the prediction result endpoint or use a webhook.
Which input does Image Edit require?
Send a prompt describing the edit and an image_url pointing to the source image. Local images can first be uploaded through Muapi's upload endpoint.
How is Wan 3.0 billed?
Wan 3.0 uses Muapi's pay-per-generation billing model and the completed task response includes the charge details.