ComfyUI

The most powerful open source workflow engine for visual AI

[ComfyUI @ComfyUI]

Comfy MCP is now local and open-source!

The #1 ask after Comfy Cloud MCP shipped in June.

Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs.

It is now the easiest way to help with your local Minimax H3 workflows!

Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

[ComfyUI @ComfyUI]

Try the workflows!

https://t.co/TTd9KruO3U
https://t.co/bnc0UPH3Zc

[ComfyUI @ComfyUI]

Qwen-Image-2.1 is now supported in ComfyUI!

Open weights. One 7B checkpoint that generates and edits.

→ Image generation at native 2K
→ Instruction editing from up to 10 reference images in a single pass
→ RGBA output, alpha included

[ComfyUI @ComfyUI]

https://t.co/GVuJ1Q8fEF

[ComfyUI @ComfyUI]

A fight sequence built around two character references and a location using Seedance 2.5.

Prompt + workflow included.

Link below 👇

[ComfyUI @ComfyUI]

@intocryptoast @higgsfield Sent you a DM!

[ComfyUI @ComfyUI]

Run the workflow: https://t.co/856BZ0Xhhk

[ComfyUI @ComfyUI]

ComfyUI for Animation: Concept Art to Any Angle

Concept art → 3D proxy → any angle you want. One graph, two methods.

Step 1: load your concept art. Tripo generates a 3D model and saves it as a GLB. Drag it into Load 3D and set material mode to Normal.

Step 2 (stills): rotate the viewport to your angle. Load 3D outputs the view, and GPT Image 2 renders it back as a polished on-style illustration.

Step 3 (camera moves): record a path in the viewport. That clip becomes the motion reference for Seedance 2.0, which generates the move through the stylized scene.

Click the link below to run the workflow ⬇️

[ComfyUI @ComfyUI]

https://t.co/5wmrQQYiSc

[ComfyUI @ComfyUI]

Creators IG: https://t.co/kMGadDbpwX

[ComfyUI @ComfyUI]

The camera is becoming optional in commercial production.

Creator park_in_su ( IG ) made an outdoor commercial now playing on Seoul's Han River Bus lines, built with AI from start to finish in ComfyUI using Seedance 2.5.

→ Commercial concept, no filming
→ Seedance 2.5 generating in ComfyUI
→ Final spot running on the Han River Bus lines

The bar isn't "good for AI" anymore. It's good enough to run in public.

[ComfyUI @ComfyUI]

https://t.co/zXLl9RtBz0

[ComfyUI @ComfyUI]

A fictional shoe commercial built from 6 different reference images,j including the character, environment, logo, dog, and other elements.

Seedance 2.5 brings them together with natural, human-style movement while keeping the product and narrative clear.

To try this workflow, link below 👇

[ComfyUI @ComfyUI]

Image 2 Video: https://t.co/yvLb4oKbli

[ComfyUI @ComfyUI]

FastH3 by FastVideo is now available in ComfyUI

Video and native stereo audio, generated together, in seconds.

Best for:

→ Previz and animatics that need lots of takes, quickly
→ Timing and dialogue tests before committing to a full-quality render
→ Short-form and social work on tight turnarounds

Run it locally in ComfyUI and soon on Cloud ⬇️

[ComfyUI @ComfyUI]

Text 2 Video: https://t.co/S1RZUh3uIU

[ComfyUI @ComfyUI]

@0xWuki Appreciate the words! 🤝

[ComfyUI @ComfyUI]

ComfyUI for Advertising: Product Photography to Hero Video (GPT Image + Seedance)

Product shot → retouch → hero video. Three steps, one graph.

Step 1: load your product and an optional background. GPT Image places it into the scene.

Step 2: mask what you want changed and prompt the fix. GPT Image edits just those areas.

Step 3: hand the final photo to Seedance. It comes back as a hero shot, a slow orbit by default.

Works with your existing product shots too.

[ComfyUI @ComfyUI]

Run the workflow: https://t.co/fqCzBgE71e

[Robin Huang @robinjhuang]

In 9 days, OpenAI switches off the Sora 2 API.

Sept 24: sora-2, sora-2-pro, every snapshot. Gone.

If your workflow was prompt in, clip out, you're rebuilding.

If the model was one node, you're swapping it.

Models are rentals. Workflows are property.

[ComfyUI @ComfyUI]

https://t.co/RUr5LLLQZk

[ComfyUI @ComfyUI]

Turn a single talking-head video into multiple camera angles with Seedance 2.5.

A simple way to add more visual variety to someone speaking on camera without sticking to one static shot.

To try this workflow, link below 👇