Starstruk Logo MarkStarstruk

v0.28.0

plausible/analyticsv0.28.0Jul 15, 2026by github-actions[bot]

AI Summary

ComfyUI v0.28.0 introduces support for Seedream 5 Pro and SeedVR2 models, alongside significant performance optimizations for int8 and int4 models on Turing GPUs. The release also includes security fixes, removal of deprecated partner nodes (StabilityAI, Ideogram V1/V2), and new features like a basic text overlay node and 3D advanced nodes.

Key Highlights

  • Added support for Seedream 5 Pro and SeedVR2 models
  • Optimized int8 and int4 models for Turing GPUs
  • Removed deprecated partner nodes (StabilityAI, Ideogram V1/V2)
  • Fixed four security vulnerabilities (GHSA-779p-m5rp-r4h4)
  • Added basic text overlay node (CORE-137)

Breaking Changes

  • Removed StabilityAI nodes
  • Removed Ideogram V1 and Ideogram V2 nodes
  • Dropped support for PyTorch 2.4

New Features

  • Basic text overlay node implementation
  • New asset hashing option via --enable-asset-hashing
  • API exposure of effective extension filter on /experiment/models
  • Support for gqa on all attention backends
  • Convrot int4 model support

Full Release Notes

## What's Changed
* Add AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14696
* Add some more stuff to AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14704
* Fix Qwen3-VL tokenizer crash with custom embeddings by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/14713
* Update AGENTS.md with more stuff. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14725
* [Partner Nodes] chore(Ideogram): remove IdeogramV1 and IdeogramV2 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14712
* Update AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14726
* security: fix four vulnerabilities (GHSA-779p-m5rp-r4h4) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14734
* Update AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14733
* [Partner Nodes] feat(ByteDance): add support for Seed Audio 1.0 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14731
* Update workflow templates to v0.11.2 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14741
* [Partner Nodes] chore(StabilityAI): remove StabilityAI nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14737
* Update AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14738
* [Partner Nodes] chore(ByteDance): adjust category name by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14752
* Add CLAUDE.md as symlink to AGENTS.md by @robinjhuang in https://github.com/Comfy-Org/ComfyUI/pull/14757
* fix: error when embedding is loaded with models using llama_template by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/14744
* Try to make coderabbit enforce AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14759
* fix: Bug when setting transparency in color picker by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14764
* [Partner Nodes] fix(logs-auth): mask authorization headers in logs by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14774
* Small speedup for text model sampling. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14773
* Update embedded docs to v0.5.7 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14783
* Skip unloading dynamic model patchers in current workflow. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14799
* ci: add CLA Assistant workflow by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14582
* Delete symlink that breaks our updates. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14803
* fix(Video): don't crash on videos with undecodable audio streams by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14746
* feat: Implement basic text overlay node (CORE-137) by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/14610
* Update AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14819
* Support gqa on all attention backends, drop support for pytorch 2.4 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14772
* Fix crash when using UNetSelfAttentionMultiply by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14823
* add models-directory launch argument by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/9113
* Fix AttributeError in VAE.is_dynamic() for VAEs constructed without a patcher by @j2gg0s in https://github.com/Comfy-Org/ComfyUI/pull/14826
* [Partner Nodes] feat(ByteDance): add Seedream 5 Pro model support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14832
* Update workflow templates to v0.11.6 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14834
* feat(assets): add namespaced model_type tags and align tag semantics by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/14511
* Fix qwen3vl reference images when used as a text encode models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14845
* feat: allow --comfy-api-base target ephemeral testenvs by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14569
* fix: Load3D failing path validation from double path resolution by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14852
* feat(api): expose effective extension filter on /experiment/models by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/14797
* Update cla.yml by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14851
* Support convrot int4 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14859
* Try to fix the model reloading issue some people have. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14822
* Fix FP8 activation quantization for >2D activations in mixed_precision_ops by @liminfei-amd in https://github.com/Comfy-Org/ComfyUI/pull/14643
* Enable comfy-kitchen Triton backend by default on ROCm/AMD by @liminfei-amd in https://github.com/Comfy-Org/ComfyUI/pull/14862
* Fix black image on turing when using int4 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14864
* Add SeedVR2 support (CORE-6) by @pollockjj in https://github.com/Comfy-Org/ComfyUI/pull/14424
* [Partner Nodes] feat(Seedream): add widget to disable thinking by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14853
* [Partner Nodes] fix(Tencent): restore Tencent3DPartNode FBX output by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14867
* Only auto-enable the ROCm comfy-kitchen Triton backend on matrix-core GPUs by @liminfei-amd in https://github.com/Comfy-Org/ComfyUI/pull/14869
* Save Text Node (CORE-176) by @yousef-rafat in https://github.com/Comfy-Org/ComfyUI/pull/14102
* feat: add bboxes input to Create Bounding Boxes node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14724
* CORE-329 feat: add Save 3D (Advanced) node family by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14701
* fix: Undeprecate the text node by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14870
* chore: Update preview nodes by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14871
* Try to fix some issues with the seedvr VAE. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14877
* Temporarily disable auto enabling triton by default on AMD. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14878
* Try to fix flash attention related issue on AMD. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14880
* Fix SaveVideo description: says images, saves video by @gmhelmold in https://github.com/Comfy-Org/ComfyUI/pull/14885
* Support PID 1.5 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14894
* [Partner Nodes] feat(client): send ComfyUI Core version in request headers by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14910
* fix(image): correct HLG inverse-OETF clamp in hlg_to_linear by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14762
* fix(image): support single-channel images in Save Image (Advanced) by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14761
* [Partner Nodes] chore(Google): reroute Gemini Image preview models to release versions by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14917
* Update embedded docs to v0.5.8 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14920
* chore(openapi): sync shared API contract from cloud@491db61 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14815
* Update workflow templates to v0.11.9 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14924
* Fix hidream o1 regression. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14923
* More optimized int8 and int4 on turing. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14927
* Fix 3D advanced nodes crashing in API mode (no UI) by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14930
* Fix int8 performance regression on 16xx series. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14941
* [Partner Nodes] feat(sync.so): add support for "sync-3" model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14928
* Fix cached outputs missing from job results when prompt has no client_id by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14939
* Bump comfyui-frontend-package to 1.45.21 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14944

## New Contributors
* @j2gg0s made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14826
* @liminfei-amd made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14643
* @gmhelmold made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14885

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.27.0...v0.28.0