ComfyUI Files

What's Changed

• Faster workflow cancelling. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10301
• Python 3.14 instructions. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10337
• api-nodes: fixed dynamic pricing format; rename comfy_io to IO by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10336
• Bump frontend to 1.28.6 by @arjansingh in https://github.com/comfyanonymous/ComfyUI/pull/10345
• gfx942 doesn't support fp8 operations. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10348
• Add TemporalScoreRescaling node by @chaObserv in https://github.com/comfyanonymous/ComfyUI/pull/10351
• feat(api-nodes): add Veo3.1 model by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10357
• Latest pytorch stable is cu130 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10361
• Fix order of inputs nested merge_nested_dicts by @Kosinkadink in https://github.com/comfyanonymous/ComfyUI/pull/10362
• refactor: Replace manual patches merging with merge_nested_dicts by @neverbiasu in https://github.com/comfyanonymous/ComfyUI/pull/10360
• Bump frontend to 1.28.7 by @arjansingh in https://github.com/comfyanonymous/ComfyUI/pull/10364
• feat: deprecated API alert by @LittleSound in https://github.com/comfyanonymous/ComfyUI/pull/10366
• fix(api-nodes): remove "veo2" model from Veo3 node by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10372
• Workaround for nvidia issue where VAE uses 3x more memory on torch 2.9 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10373
• workaround also works on cudnn 91200 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10375
• Do batch_slice in EasyCache's apply_cache_diff by @Kosinkadink in https://github.com/comfyanonymous/ComfyUI/pull/10376
• execution: fold in dependency aware caching / Fix --cache-none with loops/lazy etc by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10368
• [V3] convert nodes_controlnet.py to V3 schema by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10202
• Update Python 3.14 installation instructions by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10385
• Disable torch compiler for cast_bias_weight function by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10384
• Turn off cuda malloc by default when --fast autotune is turned on. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10393
• Fix batch size above 1 giving bad output in chroma radiance. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10394
• Speed up chroma radiance. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10395
• Pytorch is stupid. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10398
• Deprecation warning on unused files by @christian-byrne in https://github.com/comfyanonymous/ComfyUI/pull/10387
• Update template to 0.2.1 by @comfyui-wiki in https://github.com/comfyanonymous/ComfyUI/pull/10413
• Log message for cudnn disable on AMD. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10418
• Revert "execution: fold in dependency aware caching / Fix --cache-none with loops/lazy etc" by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10422

New Contributors

• @neverbiasu made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/10360
• @LittleSound made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/10366

Full Changelog: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.65...v0.3.66