Text to video: build a plush space adventure from a written prompt.
Updated August 2026
Wan 3.0
Wan 3.0 is a step change from previous Wan models. It generates what earlier versions couldn't: a full 30-second scene in one take, as low as 480p for speed and iteration, and up to 1080p for production quality. Available on Comfy Cloud and via Partner Nodes today.
Made with
Wan 3.0
Choose a plan
Access cloud-powered ComfyUI workflows with straightforward, usage-based pricing.
Start Comfy Cloud for free. Upgrade when you're ready.
5 free runs on real GPUs — no credit card required.
Billed monthly
What's included:
- Included: 30 minute max workflow runtime
- Included: Add more credits anytime
Comfy Agent
- Included: 4 concurrent agent sessions per workspace
Comfy API
- Included: 5 builds
- Included: 2 deployments
- Included: Up to 2 workers per deployment
Generates ~380 5s videos*
Billed monthly
Everything in Standard, plus:
- Included: Import your own models
Comfy Agent
- Included: 6 concurrent agent sessions per workspace
Comfy API
- Included: 5 builds
- Included: 2 deployments
- Included: Up to 2 workers per deployment
Generates ~670 5s videos*
Billed monthly
Everything in Creator, plus:
- Included: Longer workflow runtime (up to 1 hr)
Comfy Agent
- Included: 8 concurrent agent sessions per workspace
Comfy API
- Included: 10 builds
- Included: 5 deployments
- Included: Up to 10 workers per deployment
Generates ~1,915 5s videos*
Built for teams collaborating on workflows together.
Billed monthly
Generates ~13,405 5s videos*
Everything in Pro, plus:
- Included: Invite members
- Included: Members can run workflows concurrently
- Included: Shared credit pool for all members
- Included: Role-based permissions
Comfy Agent
- Included: 16 concurrent agent sessions per workspace
Comfy API
- Included: 40 builds
- Included: 20 deployments
- Included: Up to 20 workers per deployment
Coming soon...
- Coming soon: Shared workflows & assets
- Coming soon: Projects
Need more members? Looking for more flexibility or custom features?
*Based on 5s videos created with the Wan 2.2 Image-to-Video template using default settings (81 frames, 18fps, 640x640, 4-step sampler)
Q&A
Alibaba's latest video model. Give it a prompt, up to 20 reference assets, or even a document and it generates up to 30 seconds with native audio.
Native 30-second clips, up to 20 reference inputs, and 480p generations for quick and cost effective generations.
This model ships with three workflows available in the template library — reference to video, image to video and text to video.
Start simple: subject, scene, motion — one sentence is enough for a full clip. For more control, layer in camera movement, lighting, style, and sound, or address your uploads directly with @ syntax: "@Image1 walks through the door and says the line from @Audio1." The longer and more precise the prompt, the closer the output tracks your intent — it accepts up to 20,000 characters.
Yes. Describe the change — remove an object, relight the scene, swap a subject — and everything else in the frame stays put. It can also extend existing footage.
Anywhere from 2 to 30 seconds, generated in one continuous take — no stitching. Audio is generated natively, or switch it off.
One engine, every way to run it
Build workflows in the browser today. Batch campaigns with the API, or bring it in-house.
Comfy MCP: now turn your agent into a creative technologist.
Your AI assistant can access the ecosystem, build workflows, and generate images, video, audio, or 3D.