
ComfyUI v0.39.0 Release Updates
The latest release of ComfyUI, a GitHub project, brings several updates and improvements, including support for LynnReal light Minimax-H3 vae and updated embedded docs.
9 stories · since April 24, 2026

The latest release of ComfyUI, a GitHub project, brings several updates and improvements, including support for LynnReal light Minimax-H3 vae and updated embedded docs.

Subtopic Small Models · Vision Language · Quantization Takeaways − Mitsuba is a ternary 1.58-bit quantization of Qwen3.8-27B, shrunk to 7.3 GB for a single 16 GB GPU. Purpose-built for ComfyUI: image to prompt generation for Stable Diffusion, Krea, and video pipelines.

How to install ComfyUI on Mac to generate AI images locally How to install ComfyUI on Mac to generate AI images locally Step by step guide to install ComfyUI on an Apple Silicon Mac and generate AI images with FLUX locally, no subscriptions or cloud needed. 1.

Alibaba s Qwen team shipped Qwen-Image-2.1 on September 20, 2026, and it changes the calculus for anyone running AI image generation on their own hardware in Australia. The 20-billion-parameter model handles text-to-image generation, multi-reference editing with up to 10 source images, and native transparent PNG output from a single checkpoint.

MiniMax H3 now runs natively in ComfyUI 0.30.0 or later. The official templates cover text-to-video, image-to-video and multimodal reference-to-video, producing video and synchronized 32 kHz stereo audio in one MP4.

😺 Watch: ComfyUI Proves AI Art Is Not Zero Effort 😺 Watch: ComfyUI Proves AI Art Is Not Zero Effort 😺 Watch: ComfyUI Proves AI Art Is Not Zero Effort Make images & video w/ AI for free on your computer Your browser does not support the audio element.

Comfy Org is turning one of AI image generation's most flexible open-source tools into something far easier to install, manage and use at work. ComfyUI has always had a powerful pitch: build visual AI workflows exactly the way you want them, node by node, model by model, without waiting for a closed platform to decide what matters.

How to Build, Run, and Scale High-Quality Creator Workflows in ComfyUI | NVIDIA Technical Blog How to Build, Run, and Scale High-Quality Creator Workflows in ComfyUI By Joel Pennington , Margaret Zhang and Maitri Taneja NVIDIA GenAI Creator Toolkit provides three production-ready ComfyUI workflows that run locally on NVIDIA RTX GPUs without cloud dependencies.

ComfyUI hits $500M valuation as creators seek more control over AI-generated media | TechCrunch Last day to exhibit your breakthrough to 10,000+ tech leaders at Disrupt is on Oct 2 . Book Exhibit Table Now.