ComfyUI 0.40.0

What's Changed

• [Server.py] Update CSP to allow blob: and data: by @S0yKaf in https://github.com/Comfy-Org/ComfyUI/pull/15565
• Add comfy_attention and AttentionTensorContainer support to rest of models by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16806
• Implement the asset export API locally (CORE-454) by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/16578
• Report 3D models from every 3D node as a standard 3d output item by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/16200
• feat(camera-info): CreateCameraInfo node + CameraInfoState widget input by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14964
• feat(assets): extract video metadata into system_metadata on ingest and scan by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15180
• Add a way to attach metadata to the websocket messages of a prompt. by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16763
• fix: preserve dynamic input validation and lazy execution by @jaeone94 in https://github.com/Comfy-Org/ComfyUI/pull/16377
• refactor: keep DynamicGroup internal while stabilizing by @jaeone94 in https://github.com/Comfy-Org/ComfyUI/pull/16811
• feat: add CameraAngle node with camera_info and shot prompt outputs by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/16251
• [Partner Nodes] feat(Google): add Nano Banana 2.1 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16822
• Update workflow templates to v0.11.77 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16823
• Improve low VRAM performance of qwen 3.5 LLM by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16820
• Make k/v contiguous before SDPA on gfx1151 when they don't fit in L2 by @tvukovic-amd in https://github.com/Comfy-Org/ComfyUI/pull/16726
• Consolidate Linear forward API with prologue/epilogue fusion paths by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16816
• Also attach the metadata to a prompt's preview image frames. by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16809
• Add governance enforcement for custom nodes by @guill in https://github.com/Comfy-Org/ComfyUI/pull/16167
• comfy_attention configs in model files can now use kitchen sol attention. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16831
• Bump comfyui-frontend-package to 1.55.14 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/16736
• [Partner Nodes] feat(Quiver): add V2 SVG nodes with per-model inputs and deprecate the originals by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16775
• [Partner Nodes] feat(Vidu): add nodes for Vidu Q4 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16849
• [Partner Nodes] feat(ClarityAI): add Crystal Upscaler node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16817
• [Partner Nodes] feat(Kling): add Kling Virtual Try-On node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16844
• Update workflow templates to v0.11.78 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16851
• Change model code to use function wrappers for Linear calls by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16861
• Fix issue with bypass loras and fused paths. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16862
• Use PNG compress level 4 for GLB textures for faster saving by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16867
• Comfy Aimdo 0.5.6 + Fix qwen 2.1 rogues in low VRAM conditions by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16870
• Fix Qwen3.5 MTP embedding offload by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16877
• Loras can now replace the per layer attention config on a model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16880
• Link related repositories in CodeRabbit reviews by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16769
• feat: add native LoRA stack loader nodes (CORE-186) by @jaeone94 in https://github.com/Comfy-Org/ComfyUI/pull/16309
• Turn the assets system on by default; add --disable-assets by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16884
• [Partner Nodes] feat(HeyGen): add 2k resolution to HeyGen Video 1.0 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16876
• Add LatentOperationBlend and start/end percent to LatentApplyOperatio... by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16923
• Disable the output assets scanning. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16926
• Enable MTP with images on Qwen3.5 by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16922
• Decode MiniMax H3 single images as the first latent of a clip by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16881
• fix(assets): date scanned assets by their file's mtime by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16810
• Enable compression on saved EXR. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16948
• Fix issues with loading half float files with pyav. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16949
• Keep linked repository findings focused by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16920
• Remove some outdated code. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16960
• Turn assets off unless --enable-assets, and scan the output folder again by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16929
• Turn the assets system on for the Windows standalone build by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16928
• Add a ARM64 nvidia portable. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16985
• Remove the cryptography package dependency. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16988
• Update embedded docs to v0.5.14 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16981
• [Partner Nodes] feat(Higgsfield): Genjutsu Motion Transfer node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16913
• feat(assets): previews for EXR assets, written by SaveImageAdvanced for outputs by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16898
• [Partner Nodes] feat(FishAudio): add Drama 3 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16999
• Update workflow templates to v0.11.82 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/17001
• Bump comfyui-frontend-package to 1.55.17 by @AustinMroz in https://github.com/Comfy-Org/ComfyUI/pull/17004

New Contributors

• @S0yKaf made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15565

Full Changelog: https://github.com/Comfy-Org/ComfyUI/compare/v0.39.0...v0.40.0