Starstruk Logo MarkStarstruk

v0.34.0

Comfy-Org/ComfyUIv0.34.0Aug 26, 2026by github-actions[bot]

AI Summary

This release focuses on performance improvements and new model support, including HDR video capabilities and several partner integrations like Wan 3.0 and Pixverse V6, alongside optimizations for dynamic VRAM and Gemma4.

Key Highlights

  • Gemma4 text generation speedup
  • HDR video saving with AV1 codec support
  • New partner nodes: Wan 3.0, Pixverse V6, Pixal3d/Trellis2, Sam3d-body
  • Dynamic VRAM enabled by default on ROCm 7.14+
  • Minimax-H3 support and thinking handling fix

New Features

  • HDR color space options and bit depth changes for video codecs
  • Pixal3d and TRELLIS2 3D model support
  • Sam3d-body 3D model support
  • Wan 3.0 video generation nodes
  • Pixverse V6 model support
  • Seedream node with Fast Mode widget (ByteDance)
  • Flux Video Upscale node (BFL)
  • vCube Video Enhance node (ByteDance)
  • Minimax Music 3 support

Full Release Notes

## What's Changed
* Fix minimax music not working on non dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15588
* Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15439
* chore(openapi): sync shared API contract from cloud@94d0f1b by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15041
* Bump comfyui-frontend-package to 1.49.6 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15526
* Speedup Gemma4 text generation (CORE-371) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15054
* Update embedded docs to v0.5.10 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15613
* Fix thinking handling by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15611
* Enable dynamic vram by default on ROCm 7.14 and higher. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15633
* [Partner Nodes] feat(ByteDance): add Seedance 2.5 task_type for video extension by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15579
* [Partner Nodes] Stop adding an opaque alpha channel to API node images by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15369
* fix(tests): accept Python 3.14 math error messages by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15645
* Add Minimax Music 3 to readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15656
* [Partner Nodes] feat(x-comfy-credits): remove custom price extractor logic by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15655
* Allow regular single image Empty Latent Image node to be used with H3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15677
* [Partner Nodes] chore(Kling): remove kling-v2 image model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15676
* Forward node class attributes into schema for dataset nodes by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15683
* [Partner Nodes] feat(FishAudio): implement basic nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15612
* [Partner Nodes] feat(ByteDance): add 1080p resolution to Seedance 2.5 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15684
* Update workflow templates to v0.11.43 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15690
* Support per-token video and audio latent noise masks on MiniMax-H3 by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15375
* Add support for taeh3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15695
* feat(minimax): support prompt embeddings by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/15697
* Keep temp-directory assets visible while their files exist by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15510
* Prs/ace graphs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15698
* Drop the duplicate first image from the Qwen-Image-Layered blueprint by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15364
* Add friendly errors to the dynamic vram safetensors loader. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15722
* Fix missing asset preview URLs outside input and output by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15509
* [Partner Nodes] Add Gemini 3.7 Flash to the Gemini text node text node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15688
* Limit Windows multi-GPU visibility (CORE-391) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15737
* [Partner Nodes] chore(Prune): rename Ideogram P-Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15751
* [Partner Nodes] feat(Bytedance): add new Seedream node with Fast Mode widget by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15750
* [Partner Nodes] feat(BFL): add Flux Video Upscale node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15753
* Update workflow templates to v0.11.44 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15754
* ci: add Notify on Merge dispatch workflow by @luke-mino-altherr in https://github.com/Comfy-Org/ComfyUI/pull/15568
* Support HDR video saving, AV1 codec, mkv and webm. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15741
* Add HDR color space options to h264 codec in Save Video node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15764
* fix: fail CLA allowlist step on API errors by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/15792
* feat: Support Pixal3d and TRELLIS2 (CORE-278) (CORE-199) (CORE-236) (CORE-312) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14718
* Increase trellis2 memory factor a bit. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15796
* [Partner Nodes] feat(ByteDance): add vCube Video Enhance node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15755
* Minimax-H3: Add missing special tokens by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15808
* Add colorspace option and change bit_depth to a combo on CreateVideo. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15810
* Default Windows to the first CUDA device by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15813
* feat: Support Sam3d-body (CORE-35) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14370
* Increase minimum pyav version. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15827
* [Partner Nodes] feat(Wan): add Wan 3.0 video generation nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15843
* [Partner Nodes] feat(Meshy): add Meshy-7 support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15807
* Update workflow templates to v0.11.46 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15864
* Mark Compare Image node as not experimental anymore by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/15868
* Fix default database path for custom user directory by @Constantine1916 in https://github.com/Comfy-Org/ComfyUI/pull/14539
* Python 3.10 will be EOL soon, please upgrade. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15874
* [Partner Nodes] chore(Tripo): remove retired Refine node and v2.0 model version by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15851
* comfy-aimdo 0.4.15 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15886
* [Partner Nodes] feat(Pixverse): add Pixverse V6 model support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15880
* Update workflow templates to v0.11.48 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15888

## New Contributors
* @Constantine1916 made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14539

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.33.0...v0.34.0