Starstruk Logo MarkStarstruk

v0.19.0

Comfy-Org/ComfyUIv0.19.0Apr 13, 2026by github-actions[bot]

AI Summary

This release introduces support for several new AI models including LTX2, Qwen3.5, Ace Step 1.5 XL, and RT-DETRv4, alongside new utility nodes like Curve and Number Convert. It also includes backend optimizations for fp8 support and RAM cache integration.

Key Highlights

  • Support for LTX2 reference audio (ID-LoRA)
  • Add Qwen3.5 text generation models
  • Support Ace Step 1.5 XL model
  • Support RT-DETRv4 detection model
  • Add Curve node and Image Histogram node

New Features

  • LTX2 reference audio support
  • Qwen3.5 support
  • Ace Step 1.5 XL support
  • RT-DETRv4 support
  • Curve node
  • Number Convert node
  • Image Histogram node
  • Ernie Image model
  • fp8 backward support (experimental)
  • RAM cache integration

Full Release Notes

## What's Changed
* LongCat-Image edit by @Talmaj in https://github.com/Comfy-Org/ComfyUI/pull/13003
* Add warning for users who disable dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13113
* bump manager version to 4.1b8 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/13108
* feat: LTX2: Support reference audio (ID-LoRA) (CORE-16) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13111
* Update frontend version to 1.42.8 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13126
* fix: set default values of Color Adjustment node to zero by @kaili-yang in https://github.com/Comfy-Org/ComfyUI/pull/13084
* feat(api-nodes): update xAI Grok nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13140
* Update templates package version. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13141
* CURVE node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/12757
* Add Number Convert node by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/13041
* [Trainer/Experimental] Support fp8 backward by @KohakuBlueleaf in https://github.com/Comfy-Org/ComfyUI/pull/13121
* feat(assets): register output files as assets after prompt execution by @luke-mino-altherr in https://github.com/Comfy-Org/ComfyUI/pull/12812
* Fix Train LoRA crash with training_dtype "none" and bfloat16 LoRA weights by @Krishnachaitanyakc in https://github.com/Comfy-Org/ComfyUI/pull/13145
* [API Nodes] made Reve node price badges more precise by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13154
* bump manager version to 4.1 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/13156
* fix(number-convert): preserve int precision for large numbers by @dante01yoon in https://github.com/Comfy-Org/ComfyUI/pull/13147
* CORE-15 feat: Support Qwen3.5 text generation models by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12771
* fix(assets): recognize temp directory in asset category resolution by @luke-mino-altherr in https://github.com/Comfy-Org/ComfyUI/pull/13159
* Make Qwen 8B work with TextGenerate node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13160
* fix: regression in text generate with LTXAV model by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13170
* [API Nodes] add new Topaz model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13175
* Update workflow templates to v0.9.38 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13176
* feat: add curve inputs and raise uniform limit for GLSL shader node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13158
* Fix blur and sharpen nodes not working with fp16 intermediates. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13181
* fix: register image/svg+xml MIME type for .svg files by @viva-jinyi in https://github.com/Comfy-Org/ComfyUI/pull/13186
* Update workflow templates to v0.9.39 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13196
* fix(api-nodes-nanobana): raise error when not output image is present by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13167
* Allow flux conditioning without a pooled output. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13198
* Add has_intermediate_output flag for nodes with interactive UI by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13048
* Integrate RAM cache with model RAM management by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13173
* fix: avoid nested sampler function calls in Color Curves shader by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13209
* Fix #13214 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13216
* feat: Support RT-DETRv4 detection model (CORE-13) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12748
* [Partner Nodes] Tencent3D update by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13207
* Fix/tweak pinned memory accounting by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13221
* Update README.md with latest AMD Linux pytorch. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13228
* Rename utils/string nodes with Text prefix and add search aliases by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/13227
* Update README with note on model support by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13235
* Fix some fp8 scaled checkpoints no longer working. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13239
* Update workflow templates to v0.9.41 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13242
* Remove dead code. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13251
* Fix some issue with insecure browsers. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13261
* [API Nodes] add new nodes for WAN2.7 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13264
* Update template to 0.9.43 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13265
* Add portable release for intel XPU. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13272
* Nightly Nvidia pytorch is now cu132 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13288
* Update workflow templates to v0.9.44 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13290
* Update README.md with new frontend release cycle. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13301
* image histogram node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13153
* Ace step empty latent nodes follow intermediate dtype. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13313
* format blueprint by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13315
* feat: Support Ace Step 1.5 XL model (CORE-39) by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13317
* Add support for small flux.2 decoder by @huemin-art in https://github.com/Comfy-Org/ComfyUI/pull/13314
* Basic intel standalone package .bat by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13333
* Bump comfyui-frontend-package version to 1.42.10 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13346
* should use 0 as defalut for brightness by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/13345
* [Partner Nodes] fix GrokVideoReferenceNode price badge by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13354
* Update workflow templates to v0.9.45 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13353
* fix: SDPose - resize input always by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13349
* Make ImageUpscaleWithModel node work with intermediate device and dtype. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13357
* Add a supports_fp64 function. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13368
* Implement Ernie Image model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13369
* Update quant doc so it's not completely wrong. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13381
* Fix typo. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13382
* [Partner Nodes] add SeeDance 2.0 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13364
* Update workflow templates to v0.9.47 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13385

## New Contributors
* @kaili-yang made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/13084
* @Krishnachaitanyakc made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/13145
* @huemin-art made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/13314

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.18.1...v0.19.0