ComfyUI now has Traditional Chinese support! A huge thanks to Christian Byrne

ComfyUI now supports nano-banana via native API Nodes! 🔹 Supports both text-to-image & image-to-image generation 🔹 Impressive character consistency and fidelity 🔹 Text output capability 🔹 Customizable resolutions & aspect ratios Getting Started 1. Update ComfyUI to the

In our first week's Comfy Challenge, we asked our community to turn a cat image around — we ended up receiving over 400 submissions from the community! We were blown away!! ✨ Check the spotlight montage here!

📹 Challenge Round #2: “Falling” A video starts with a scene of an object or character falling. Made in ComfyUI, 1:1 ratio, < 20 seconds 🪙 Prize $100 cash or ComfyUI credits for 1 Spotlight Montage for selected entries ❓ A special gift (WIP) For participants since Week 1

Wan2.2-S2V is now natively supported in ComfyUI! Transform static images and audio into cinematic-quality videos with synchronized lip-sync and natural movements. 🔹 Audio-driven video generation 🔹 Cinematic-grade quality output 🔹 Minute-level long-form videos 🔹 Multi-format

Who knew? You can move all output links from one node to another—just hold the Shift key while moving them. Not me... till today. 🥲 I bet there are still a lot of tricks they are hiding.

Qwen-Image InstanX Inpainting ControlNet Workflow👉: x.com/ComfyUI/status…

From hackers to studios, millions already build with ComfyUI. Today, we’re taking it further: Comfy Cloud 🌩️ The full power of ComfyUI, now in your browser. No installs. No limits. Just create. Join private beta for free👇

Open source lasts forever ❤️

ComfyUI now natively supports HuMo and Chroma 1 Radiance HuMo - Human-centric video generation with audio sync Chroma1-Radiance - Pixel-space image generation (no VAE!) Try it now in ComfyUI👇

ComfyUI 0.3.63 now supports Subgraph Publishing! Select any subgraphs, publish with one click. Re-use, re-edit, like a single node. Find your subgraphs in the Node Library. Update ComfyUI and try it now👇

I really like this new launch page 😍

Hugging Face OSS alternative

loool

We tried to stress-test current image generation models for every possible real-world task. What we found reveals a lot about how today’s models see, edit, and fail. 🧵 (1/N)

Want to share the Rebalance model with you guys. It's a fine-tuned Qwen-Image model. More realism and less "AI look" — that's all this model does. Huggingface: huggingface.co/lrzjason/QwenI… Civitai: civitai.com/models/2064895…

What would you love to see improved in the next version of Qwen-Image-Edit? Let us know! 🧵👇

😶‍🌫️🕺