Never miss a release that matters
AI-powered summaries of every GitHub release.
AI Summaries
Changelogs condensed into clear, actionable insights.
Always Free
Track up to 5 packages at no cost, forever.
Weekly Digest
A curated summary of every release, delivered weekly.
TL;DR
ComfyUI now supports the Qwen3-VL model (large language model with vision capabilities), expanding text-to-image and multimodal workflows.
New
- Qwen3-VL Support: Generate images and text using the Qwen3-VL model.
- Boogu-Image Support: Added support for the Boogu-Image model.
- Load3DAdvanced Node: New node for advanced 3D model loading.
Fixes Worth Knowing
- Startup now logs the base directory when using the
--base-directoryflag. - Partner nodes (Kling, Luma, Google) have been updated with new model support and improved error handling.
- Fixed an issue with loading training dataset shards.
Before You Upgrade
If you are using the desktop application, the name has been changed to “Comfy Desktop” for consistency.
TL;DR
ComfyUI now offers standalone portable Windows builds with both stable (PyTorch 2.4.1) and nightly (PyTorch 2.5) options, simplifying installation and providing access to the latest performance improvements.
Before You Upgrade
Download the desired build (stable or nightly) and extract it – no further installation steps are required.