Starstruk Logo MarkStarstruk

v0.32.0

run-llama/liteparsev0.32.0Aug 11, 2026by github-actions[bot]

AI Summary

A comprehensive update focusing on new model support (LTX 2.5, Grok), PyTorch compatibility updates, and performance optimizations.

Key Highlights

  • Added support for LTX 2.5
  • Added support for Grok-Imagine-Image-2.0
  • Updated minimum officially supported PyTorch to 2.7
  • Added Qwen-Image 3.0 Pro

New Features

  • LTX 2.5 support
  • Grok-Imagine-Image-2.0 support
  • Qwen-Image 3.0 Pro support
  • PyTorch 2.7 minimum support

Full Release Notes

## What's Changed
* Make it easier to debug nested tensors. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15383
* Update workflow templates to v0.11.37 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15415
* Minimum officially supported pytorch is now 2.7 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15413
* fix: make Create Layered Image discoverable and its flags self-explanatory by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15429
* Fix upscale models breaking on non dynamic vram low vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15437
* Add previewable_outputs_count to /api/jobs (backend half of Media Assets badge fix) by @claude[bot] in https://github.com/Comfy-Org/ComfyUI/pull/15148
* Extend ER-SDE noise scaler by scaling h(t) by @chaObserv in https://github.com/Comfy-Org/ComfyUI/pull/15428
* Make a context manager for cast_bias_weight and use it. by @blepping in https://github.com/Comfy-Org/ComfyUI/pull/14750
* Optimize MiniMax-H3 VAE by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15446
* [Partner Nodes] feat(Qwen): add Qwen-Image 3.0 Pro by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15327
* Add tags_all / tags_any / tags_none tag filters to the assets list API by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15332
* Fix VAEDecodeTiled crash on NestedTensor latents (MiniMax H3) by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/15477
* Make cu130 warning more visible. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15463
* Implement comfy kitchen attention. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15479
* Fix peak memory issue with H3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15486
* Add support for LTX 2.5 by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/15499
* [Partner Nodes] feat(LTX): add new nodes for model version 2.5 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15501
* Fix for broken tiled audio decode. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15502
* Update workflow templates to v0.11.39 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15504
* [Partner Nodes] feat(Grok): add Grok-Imagine-Image-2.0 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15496
* Fix some clip vision regression. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15506
* Don't depend on transformers for mistral and llama tokenizers. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15503
* Remove potentially problematic process_tokens method. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15507

## New Contributors
* @claude[bot] made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15148
* @chelsealong made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15477

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.31.0...v0.32.0