What's Changed
- Add test that each model has unique identifiers (CORE-134) by @Talmaj in #13654
- Make audio processing nodes handle None -inputs by @kijai in #13879
- Update workflow templates to v0.9.77 by @comfyui-wiki in #13895
- Add careers link to README and startup log by @robinjhuang in #13897
- Remove annoying message. by @comfyanonymous in #13899
- Include workflow_id in all execution WebSocket messages (CORE-198) by @christian-byrne in #13684
- Revert "Include workflow_id in all execution WebSocket messages (CORE-198)" by @comfyanonymous in #13901
- Create SECURITY.md. by @comfyanonymous in #13902
- Generalize frontend version warning to all comfy* requirements.txt entries by @christian-byrne in #13875
- Preserve noise_scale/shift across chained model_sampling patches by @kijai in #13892
- feat: Support MoGe (CORE-168) by @kijai in #13878
- Allow negative
batch_indexonImageFromBatchandLatentFromBatch(CORE-195) by @drozbay in #13857 - Reduce LTX2.3 peak VRAM when guide_mask is in use (CORE-166) by @kijai in #13735
- Remove useless option and clarify what lowvram does. by @comfyanonymous in #13922
- feat: Add downscaled IC-LoRA support to LTXVAddGuide (CORE-102) by @drozbay in #13896
- Enhance README with application and cloud links by @comfyanonymous in #13936
- Log which quant ops are enabled/emulated. by @comfyanonymous in #13946
- chore: correct OOM memory summary format by @Apophis3158 in #13950
- Fix Qwen3.5 text generation with multi-image prompts by @kijai in #13943
- HiDream-O1: support area conditioning by @kijai in #13944
- [Partner Nodes] fix Opus 4.7 sending deprecated temperature parameter by @bigcat88 in #13955
- fix(FeatherMask): correct negative zero indexing for right/bottom feathering by @alvinttang in #12881
- implement/fix dynamic clip saving by @rattus128 in #13959
- [Partner Nodes] add ByteDance Seed LLM node by @bigcat88 in #13919
- Fix BiRefNet issue by @yousef-rafat in #13966
- feat: Add optional attention_mask input to LTXVAddGuide (CORE-220) by @drozbay in #13965
- Reduce min for Batch Image/Mask/Latent nodes from 2 to 1 by @Kosinkadink in #13721
- Initial work to make downscale_ratio_temporal work. by @comfyanonymous in #13972
- chore: Various QoL updates of nodes display names, descriptions and categories (CORE-190, CORE-191) by @alexisrolland in #13830
- Use temporal downscale to make empty audio latent nodes more reusable. by @comfyanonymous in #13975
- docs(openapi): deprecate /api/upload/mask in favor of /api/upload/image by @mattmillerai in #13968
- docs(openapi): remove top-level width/height fields on Asset schema by @mattmillerai in #13973
- Fix typo in ops.py by @NAM-MAN in #11925
- feat(openapi): add optional description field to workspace API key schemas by @mattmillerai in #13993
- docs(openapi): tighten workspace API key description field (BE-1004) by @mattmillerai in #13996
- Adding new StringFormat node by @Pauan in #13997
- Add spacial downscale ratio to empty ltxv latent. by @comfyanonymous in #13999
- fix: Hunyuan3D 2.1 batch size crashes in attention and forward pass by @Kivylius in #13699
- Support Stable Audio 3 model. by @comfyanonymous in #14010
- Update workflow templates to v0.9.79 by @comfyui-wiki in #14011
New Contributors
- @Apophis3158 made their first contribution in #13950
- @NAM-MAN made their first contribution in #11925
- @Pauan made their first contribution in #13997
- @Kivylius made their first contribution in #13699
Full Changelog: v0.21.1...v0.22.0