v0.3.76

Comfy-Org/ComfyUIv0.3.76Dec 2, 2025by github-actions[bot]

AI Summary

A significant update introducing Flux 2 latent preview, Veo3 First-Last-Frame nodes, and improved batch upload UX. Includes VRAM optimizations for Flux 2 and support for the Kling O1 model.

Key Highlights

  • Cheap latent preview for Flux 2
  • Veo3 First-Last-Frame node
  • Kling O1 model support
  • Improved batch uploads
  • VRAM usage reduction for Flux 2

New Features

  • Flux 2 latent preview
  • Veo3 First-Last-Frame node
  • Kling O1 support
  • Batch upload improvements
  • Z Image support

Full Release Notes

## What's Changed
* Add cheap latent preview for flux 2. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10907
* [API Nodes] add Veo3 First-Last-Frame node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10878
* [API Nodes] improve UX for batch uploads in upload_images_to_comfyapi by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10913
* [API Nodes] fix(gemini): use first 10 images as fileData (URLs) and remaining images as inline base64 by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10918
* Bump frontend to 1.32.9 by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/10867
* Merge 3d animation node by @jtydhr88 in https://github.com/comfyanonymous/ComfyUI/pull/10025
* Fix the CSP offline feature on latest frontend. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10923
* Add Z Image to readme. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10924
* chore(api-nodes): remove chat widgets from OpenAI/Gemini nodes by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10861
* [V3] convert nodes_custom_sampler.py to V3 schema by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10206
* Dataset Processing Nodes and Improved LoRA Trainer Nodes with multi resolution supports. by @KohakuBlueleaf in https://github.com/comfyanonymous/ComfyUI/pull/10708
* Make lora training work on Z Image and remove some redundant nodes. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10927
* [BlockInfo] Flux by @Haoming02 in https://github.com/comfyanonymous/ComfyUI/pull/10841
* Account for the VRAM cost of weight offloading by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10733
* quant ops: Dequantize weight in-place (reduce flux2 VRAM usage) by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10935
* Update template to 0.7.23 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/10949
* Enable async offloading by default on Nvidia. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10953
* feat(Kling-API-Nodes): add v2-5-turbo model to FirstLastFrame node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10938
* fix(user_manager): fix typo in move_userdata dest validation by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/10967
* Disable offload stream when torch compile. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10961
* fix QuantizedTensor.is_contiguous (#10956) by @urlesistiana in https://github.com/comfyanonymous/ComfyUI/pull/10959
* mm: wrap the raw stream in context manager by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10958
* Update driver link  in AMD portable README by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10974
* Support video tiny VAEs by @kijai in https://github.com/comfyanonymous/ComfyUI/pull/10884
* Support some z image lora formats. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10978
* feat(security): add System User protection with `__` prefix by @ltdrdata in https://github.com/comfyanonymous/ComfyUI/pull/10966
* Add missing z image lora layers. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10980
* Make the ScaleRope node work on Z Image and Lumina. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10994
* update template to 0.7.25 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/10996
* Next AMD portable will have pytorch with ROCm 7.1.1 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11002
* Bumps frontend to 1.32.10 (from 1.32.9) by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/11018
* Update qwen tokenizer to add qwen 3 tokens. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/11029
* [API Nodes] add Kling O1 model support by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/11025

## New Contributors
* @urlesistiana made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/10959

**Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.75...v0.3.76