Starstruk Logo MarkStarstruk

v0.15.0

Comfy-Org/ComfyUIv0.15.0Feb 24, 2026by github-actions[bot]

AI Summary

Major release adding text generation support with native models (Gemma3), GLSL shader node, 3-band audio equalizer, and multiple new API nodes including ElevenLabs, KlingAvatar, and ByteDance Seedream-5.

Key Highlights

  • Added basic text generation support with Gemma3 native models
  • New GLSL shader node using PyOpenGL
  • Simple 3-band equalizer node for audio
  • Added essential_category and subgraph blueprints
  • Multiple new API nodes: ElevenLabs, KlingAvatar, ByteDance Seedream-5

New Features

  • Gemma3 text generation support
  • GLSL shader node
  • 3-band audio equalizer
  • Essential subgraph blueprints
  • Gradient-slider display mode for FLOAT inputs
  • BBox widget for UI
  • LTXAV av embedding connectors moved to diffusion model

Full Release Notes

## What's Changed
* ops: limit return of requants (Fix perf of some fp8 dynamic_vram workflows) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12506
* Bump comfyui-frontend-package to 1.39.14 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/12494
* BBox widget by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/11594
* fix: use glob matching for Gemini image MIME types by @huntcsg in https://github.com/Comfy-Org/ComfyUI/pull/12511
* fix(api-nodes): add price badge for Rodin Gen-2 node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12512
* Add simple 3 band equalizer node for audio. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12519
* feat: Add basic text generation support with native models, initially supporting Gemma3 by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12392
* fix(api-nodes): force Gemini to return uncompressed images by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12516
* feat: add essentials_category by @Yourz in https://github.com/Comfy-Org/ComfyUI/pull/12357
* feat: mark 429 widgets as advanced for collapsible UI by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12197
* Small cleanup and try to get qwen 3 work with the text gen. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12537
* Force min length 1 when tokenizing for text generation. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12538
* Add GLSL shader node using PyOpenGL by @pythongosssss in https://github.com/Comfy-Org/ComfyUI/pull/12148
* [API Nodes] add ElevenLabs nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12207
* chore: add CodeRabbit configuration for automated code review by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12539
* Update nightly installation command for ROCm by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12547
* Fix non-contiguous audio waveform crash in video save by @artokun in https://github.com/Comfy-Org/ComfyUI/pull/12550
* feat: add gradient-slider display mode for FLOAT inputs by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/12536
* update glsl blueprint with gradient by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/12548
* feat: add essential subgraph blueprints by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12552
* fix: swap essentials_category from CLIPTextEncode to PrimitiveStringM… by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12553
* Add support for pyopengl < 3.1.4 where the size parameter does not exist by @pythongosssss in https://github.com/Comfy-Org/ComfyUI/pull/12555
* comfy-aimdo 0.2 - Improved pytorch allocator integration by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12557
* fix: specify UTF-8 encoding when reading subgraph files by @DrJKL in https://github.com/Comfy-Org/ComfyUI/pull/12563
* Add category to Normalized Attention Guidance node by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12565
* chore: tune CodeRabbit config to limit review scope and disable for drafts by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12567
* Move LTXAV av embedding connectors to diffusion model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12569
* Fix dtype issue in embeddings connector. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12570
* Fix issue loading fp8 ltxav checkpoints. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12582
* feat(api-nodes): add KlingAvatar node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12591
* Update workflow templates to v0.9.2 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12596
* Add SplitImageToTileList and ImageMergeTileList nodes. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12599
* Temporality unbreak some LTXAV (LTX 2.0) workflows to give people time to migrate. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12605
* Patch frontend to 1.39.16 (from 1.39.14) by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12604
* feat(api-nodes): add ByteDance Seedream-5 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12609
* Update workflow templates to v0.9.3 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12610
* Don't crash right away if op is uninitialized. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12615
* Update embedded docs to v0.4.3 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/12601

## New Contributors
* @huntcsg made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12511
* @Yourz made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12357
* @artokun made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12550

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.14.1...v0.15.0