ComfyUI 动态
汇总 GitHub 上 ComfyUI 核心与前端的版本发布、Comfy 官方博客文章，以及本站发布的文章。外部链接将打开原始来源。
- 前端版本ComfyUI Frontend v1.53.8（在新标签页打开）
[backport core/1.53] fix: avoid unpolyfilled ES2023 array methods in runtime code
- 核心版本ComfyUI v0.37.4（在新标签页打开）
- 核心版本ComfyUI v0.37.3（在新标签页打开）
- 核心版本ComfyUI v0.37.2（在新标签页打开）
- 官方博客Introducing Comfy Router: One API for Frontier Media Models（在新标签页打开）
Build once, add models as they launch, and choose where every job runs.
- 核心版本ComfyUI v0.37.1（在新标签页打开）
- 官方博客Making the MiniMax H3 Video VAE 2x Faster（在新标签页打开）
The MiniMax H3 video VAE now encodes up to ~2.2x faster and decodes ~1.4-2.7x faster on Nvidia GPU.
- 前端版本ComfyUI Frontend v1.54.7（在新标签页打开）
Fix integer color input widgets
- 前端版本ComfyUI Frontend v1.53.7（在新标签页打开）
[backport core/1.53] Fix ancestor-hidden ARIA dialogs blocking shortcuts
- 核心版本ComfyUI v0.37.0（在新标签页打开）
Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440)
- 官方博客Qwen-Image-2.1 in ComfyUI: Open-Weight Image Generation and Editing, Now with Transparency（在新标签页打开）
7B parameters, native 2K output, RGBA transparency, and editing across up to 10 input images — Qwen-Image-2.1 runs natively in ComfyUI.
- 前端版本ComfyUI Frontend v1.55.11（在新标签页打开）
fix(models): stabilize credits and example layouts
- 前端版本ComfyUI Frontend v1.53.6（在新标签页打开）
[backport core/1.53] fix: retain execution errors received before prompt responses
- 核心版本ComfyUI v0.36.0（在新标签页打开）
Add new model blueprints and reorganize subgraph categories
- 核心版本ComfyUI v0.35.2（在新标签页打开）
- 前端版本ComfyUI Frontend v1.55.9（在新标签页打开）
ci: record and upload videos for newly added Playwright tests (diff-based)
- 核心版本ComfyUI v0.35.1（在新标签页打开）
- 核心版本ComfyUI v0.35.0（在新标签页打开）
[Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models
- 核心版本ComfyUI v0.34.6（在新标签页打开）
- 核心版本ComfyUI v0.34.5（在新标签页打开）
- 核心版本ComfyUI v0.34.4（在新标签页打开）
- 官方博客Forward Deployed Creatives（在新标签页打开）
Comfy experts embedded with your team, building the workflows inside your environment, and training your team to own it!
- 官方博客Comfy H3 Sync Sound Challenge: The Winners（在新标签页打开）
Two weeks, one rule, and hundreds of entries from nearly 50 countries. Here's who took the four titles, and a look at everyone who made the final ten!
- 官方博客Trellis.2 and Pixal3D Are Now Native in ComfyUI（在新标签页打开）
The best open 3D generation models are now part of ComfyUI core: no custom nodes, no dependency hell, no license traps.
- 官方博客Gemini Omni 1.1 Flash in ComfyUI: Faster Video Generation, Editing, and 4K Output（在新标签页打开）
Google's updated Omni Flash model brings 4K output, keyframe interpolation, and conversational video editing to your workflow.
- 官方博客Comfy Is Now an Official Reseller of MiniMax H3 Commercial Licenses（在新标签页打开）
Thanks for reading ComfyUI Newsletter!
- 核心版本ComfyUI v0.34.0（在新标签页打开）
Fix minimax music not working on non dynamic vram.
- 官方博客Wan 3.0 in ComfyUI: Native 30-Second Video with Omni-Reference Control（在新标签页打开）
Alibaba's new video generation model brings 30-second single-pass generation, up to 20 reference assets, and instruction-driven video editing to your workflow.
- 官方博客Comfy H3 Sync Sound Community Challenge!（在新标签页打开）
Two weeks to make something, four ways to win an RTX5090 or RTX5060 Ti, and a special guest judge livestream!
- 核心版本ComfyUI v0.33.1（在新标签页打开）
Fix KSamplerAdvanced with add_noise disabled on nested latents
来源：ComfyUI releases · ComfyUI frontend releases · blog.comfy.org · 本站更新。仅展示标题与简短摘要；ComfyUI World 与 Comfy Org 无隶属关系。