Starstruk Logo MarkStarstruk

v0.43.0

Comfy-Org/ComfyUIv0.43.0Oct 27, 2026by github-actions[bot]

Upgrading?

What changed from v0.42.1 → v0.43.0?

Release notes summary

ComfyUI v0.43.0 is a broad feature release adding expanded MOSS-image and FIBO 2.0 model support, many new Partner Nodes, and core workflow improvements. It also includes performance work for Qwen 3.x, dynamic VRAM KV caches, AMD VAE attention, and Flux2 VAE handling. New utility nodes and cloud/API-related additions round out the release.

Key Highlights

  • Expanded MOSS-image support, including RoPE scaling, color-depth control, edit LoRAs, attention-bias conditioning, image strength, and a model-specific merge node.
  • Added FIBO 2.0 support with NTK-aware RoPE scaling and negative-prompt handling fixes.
  • Major Partner Nodes expansion across HeyGen, ClarityAI, BFL FLUX 3, Bria, Krea, VEED, Mirelo, Meshy, PixVerse, Ideogram, and Kling.
  • New core nodes and capabilities including a Branch node, Pad Image node, ACEScg color-space support, and cloud endpoint deployment feature flag.
  • Performance and compatibility improvements for Qwen 3.x, dynamic VRAM KV caches, AMD VAE attention, and Flux2 VAE fusion.

New Features

  • MOSS-image RoPE scaling support
  • MOSS-image color-depth control
  • MOSS-image edit LoRA support
  • MOSS-image attention bias conditioning and image strength controls
  • Model-specific merge node for MOSS
  • FIBO 2.0 support with NTK-aware RoPE scaling
  • HeyGen Voice instant clone and text-to-speech Partner Nodes
  • ClarityAI Crystal Video Upscaler Partner Node
  • BFL FLUX 3 Video 2K/4K resolutions and FLUX 3 Max Partner Nodes
  • Bria FIBO 2.0 Image Generate/Edit and additional Bria Partner Nodes
  • Krea 3 Image ultra thinking mode
  • VEED Fabric 1.0 and Lipsync 2.0 Partner Nodes
  • Mirelo SFX Partner Nodes
  • Meshy T2.5 Smart Topology Partner Nodes
  • PixVerse V6-Max model support
  • Ideogram Vector Generate SVG Partner Nodes
  • Kling 4.0 Partner Nodes
  • Pad Image node with mirror padding and pad-to-multiple support
  • Branch node
  • ACEScg support in Convert Image Color Space and Save Image (Advanced) EXR
  • Comfy API console tips
  • Deploy to cloud endpoints with feature flag
  • Optional local agent loading through comfy-agent v1 host
  • Qwen 3.x adaptive tree MTP performance improvements
  • Dynamic VRAM KV caches part I
  • AMD VAE PyTorch attention support
  • Flux2 VAE fusion and stripping through comfy-kitchen

Full Release Notes

## What's Changed
* model_prefetch: syncrhonize all graph cleanups by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17178
* Add rope scaling support to MOSS-image by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17172
* [Partner Nodes] Renew partner-node sign-in tokens in API nodes by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/16943
* [Partner Nodes] feat(HeyGen): add HeyGen Voice instant clone and text-to-speech by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17043
* [Partner Nodes] feat(ClarityAI): add Crystal Video Upscaler node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17192
* [Partner Nodes] feat(BFL): add 2K/4K resolutions to FLUX 3 Video nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17200
* Support MOSS-image color-depth control by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17206
* Add to Readme that MOSS image is supported. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17212
* [Partner Nodes] feat(BFL): add FLUX 3 Max nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17202
* fix: correct top-p sampling threshold by @curealb in https://github.com/Comfy-Org/ComfyUI/pull/17221
* Update workflow templates to v0.11.92 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17234
* [Partner Nodes] feat(Bria): FIBO 2.0 Image Generate/Edit nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17229
* Apply single-head LoRAs to MiniMax-H3 PDD head banks by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17239
* Update workflow templates to v0.11.93 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17238
* Bump comfyui-frontend-package to 1.57.1 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/17244
* feat: Add Fibo 2.0 support by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17240
* Set minimum Pillow version in requirements. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17249
* Add Pad Image node with mirror padding and pad to multiple by @DoronGenzelHass in https://github.com/Comfy-Org/ComfyUI/pull/17224
* Load the optional local agent through comfy-agent's v1 host by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/17241
* [Partner Nodes] fix(HeyGen): update HeyGen Voice price badge by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17257
* [Partner Nodes] feat(Krea): add ultra thinking mode to Krea 3 Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17260
* [Partner Nodes] feat(VEED): add Fabric 1.0, Lipsync 2.0, and other by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17242
* [Partner Nodes] feat(Mirelo): add Mirelo SFX nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17265
* Update workflow templates to v0.11.94 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17268
* Add model integration instructions to AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17279
* Fix Gemma 4 31B global attention (k_eq_v, 4 global KV heads) by @Nynxz in https://github.com/Comfy-Org/ComfyUI/pull/17220
* Support MOSS-Image edit LoRAs by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17296
* qwen 3.x performance improvements part III - Adaptive tree MTP by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17273
* Sync offload streams before stealing a pin by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17297
* Fibo 2.0: Change RoPE scaling to NTK aware by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17290
* Fix Fibo2.0 T2I negative prompt handling by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17285
* comfy should only contain model related stuff. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17307
* Comfy-Aimdo 0.6.0 + Dynamic VRAM KV caches part I by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/17274
* [Partner Nodes] feat(Meshy): add Meshy T2.5 Smart Topology tnodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17280
* [Partner Nodes] feat(PixVerse): add PixVerse V6-Max model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17287
* [Partner Nodes] feat(Bria): add 3 new nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17289
* [Partner Nodes] feat(Ideogram): add Ideogram Vector Generate SVG nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17298
* Update workflow templates to v0.11.96 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17301
* Enable pytorch attention in the VAE on AMD by @0xDELUXA in https://github.com/Comfy-Org/ComfyUI/pull/17271
* Fuse and strip the Flux2 VAE through comfy-kitchen by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17196
* Add ACEScg to Convert Image Color Space and Save Image (Advanced) EXR (CORE-657) by @DoronGenzelHass in https://github.com/Comfy-Org/ComfyUI/pull/17023
* Add Comfy API console tips by @guill in https://github.com/Comfy-Org/ComfyUI/pull/17052
* Add attention bias conditioning and image strength for MOSS-Image edit by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17320
* Don't use pytorch attention for head dims above 256 on gfx11 by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/17323
* Update architecture boundaries in AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17331
* Lower peak MOSS memory a bit. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17338
* Add deploy to cloud endpoints and feature flag by @guill in https://github.com/Comfy-Org/ComfyUI/pull/17203
* Add a Branch node by @AustinMroz in https://github.com/Comfy-Org/ComfyUI/pull/16383
* Add model specific merge node for MOSS. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/17349
* [Partner Nodes] fix(client): respect proxy environment variables by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17346
* docs: add Huawei branding to Ascend NPU section in README by @yzeyu71 in https://github.com/Comfy-Org/ComfyUI/pull/17359
* Bump comfyui-frontend-package to 1.57.4 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/17329
* [Partner Nodes] feat(Kling): add Kling 4.0 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/17364
* Update embedded docs to v0.5.15 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17366
* Update workflow templates to v0.11.97 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17368

## New Contributors
* @curealb made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/17221
* @DoronGenzelHass made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/17224
* @Nynxz made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/17220
* @yzeyu71 made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/17359

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.42.0...v0.43.0

Related Repositories

public-apis/public-apis★ 492,766

A collective list of free APIs

NousResearch/hermes-agent★ 257,806

The agent that grows with you

yt-dlp/yt-dlp★ 203,089

A feature-rich command-line audio/video downloader

microsoft/markitdown★ 192,603

Python tool for converting files and office documents to Markdown.

Significant-Gravitas/AutoGPT★ 187,794

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.