# ComfyUI changelog

> A node-based interface for diffusion models.

- Vendor: Comfy Org
- Category: AI
- License: GPL-3.0
- Language: Python
- Official site: https://www.comfy.org
- Tracked by: What's New (https://whatsnew.fyi/product/comfyui)
- Harvested from: GitHub (comfyanonymous/ComfyUI)
- Entries below: 19 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

## Releases

### v0.39.0

- Date: 2026-10-05
- Version: v0.39.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.39.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.39.0

- **added** — Support LynnReal light Minimax-H3 vae
- **added** — Add DynamicGroup widget input
- **added** — Add Sonnet 5.5 model to Anthropic partner nodes
- **added** — Add nodes for Ideogram 4.5 model to partner nodes
- **added** — Add nodes for HeyGen Video 1.0 model to partner nodes
- **added** — Add 16-bit float support to Save EXR
- **added** — Add FLUX 3 Image node to BFL partner nodes
- **added** — Add grok-imagine-video-1.5-lite model to Grok partner nodes
- **added** — Add --offline and --disable-partner-nodes command-line options
- **added** — Add Eleven v4 and v4 Turbo models to ElevenLabs partner nodes
- **changed** — Use higher quality defaults for Save Video encoding
- **changed** — Update default bit depth for EXR option to 16 bit float
- **changed** — Disable pinned memory automatically on integrated GPUs
- **changed** — Add comfy_attention and AttentionTensorContainer support to more models
- **fixed** — Fix crash when selecting int8 or int4 cache in qwen image 2.1
- **fixed** — Fix minimax vae offload issue
- **fixed** — Fix model category scan abort issue in assets
- **fixed** — Recover asset records when a drive comes back with hashing off
- **fixed** — Batch prefix filters so scans work with many model folders
- **fixed** — Copy uploads into place when the destination is on another volume
- **deprecated** — Deprecate --disable-api-nodes command-line option
- **deprecated** — Deprecate Ray 2 nodes in Luma partner nodes

##### What's Changed
* Support LynnReal light Minimax-H3 vae by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16657
* Update embedded docs to v0.5.13 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16618
* Use higher quality defaults for Save Video encoding. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16663
* feat: add DynamicGroup widget input by @jaeone94 in https://github.com/Comfy-Org/ComfyUI/pull/16260
* fix(assets): don't let a model category that can't be listed abort the scan by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16658
* fix(assets): recover records when a drive comes back with hashing off by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16646
* Fix crash when selecting int8 or int4 cache in qwen image 2.1 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16667
* [Partner Nodes] feat(Anthropic): add Sonnet 5.5 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16647
* [Partner Nodes] feat(Ideogram): add nodes for Ideogram 4.5 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16689
* Fix minimax vae offload issue. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16698
* [Partner Nodes] feat(HeyGen): add nodes for HeyGen Video 1.0 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16695
* Update workflow templates to v0.11.73 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16693
* Add 16-bit float support to Save EXR. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16706
* Bump comfyui-frontend-package to 1.53.10 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/16456
* Release packed MiniMax H3 embedding temporaries before blocks by @Tokha233 in https://github.com/Comfy-Org/ComfyUI/pull/16677
* Update default bit depth for 'exr' option to 16 bit float. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16715
* feat: add --offline and --disable-partner-nodes, deprecate --disable-api-nodes by @deepme987 in https://github.com/Comfy-Org/ComfyUI/pull/16672
* [Partner Nodes] feat(BFL): add FLUX 3 Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16716
* [Partner Nodes] feat(Grok): add grok-imagine-video-1.5-lite model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16721
* Update workflow templates to v0.11.74 by @purzbeats in https://github.com/Comfy-Org/ComfyUI/pull/16724
* fix(assets): batch prefix filters so scans work with many model folders by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16645
* Update comfy-kitchen version to 0.2.37 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16738
* [Partner Nodes] chore(Luma): deprecate Ray 2 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16741
* Update workflow templates to v0.11.76 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16739
* Disable pinned memory automatically on integrated GPUs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16746
* feat(assets): report scan CPU and paused time, and classify scan failures by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16719
* fix(assets): don't take the database lock when assets are off; warn when it's held by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16742
* Echo the Create Bounding Boxes background as a UI preview by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/16636
* perf(assets): let the partial live-path index serve live-row-at-path lookups by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16659
* [Partner Nodes] feat(ElevenLabs): add Eleven v4 and v4 Turbo models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16737
* [Partner Nodes] fix(OpenAI): remove transparent background for GPT Image 2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16744
* fix(assets): write the prune and offline marking in short batches so saves aren't locked out by @synap5e in h

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.39.0]_

### v0.38.0

- Date: 2026-09-29
- Version: v0.38.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.38.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.38.0

- **changed** — Improve Qwen 2.1 KV cache location logic
- **changed** — Compile Qwen Image 2.1 transformer blocks
- **added** — Allow model files to contain which attention should be used for each block
- **changed** — JsonExtractString can now handle JSON with prefix and/or suffix
- **removed** — Remove torchaudio dependency
- **added** — Cuda graphs and memory compiler on ace step 1.5 autoregressive model
- **changed** — Blend H3 VAE tiles against composited neighbours
- **added** — Fast disk detection to all model loaders
- **added** — Add system_prompt input and separate thinking output to TextGenerate
- **added** — Support Fun-Controlnet-Union 2.0 for MiniMax-H3
- **fixed** — Fix MiniMax-H3 VAE rms_rope crash on offloaded qk_norm_scale
- **changed** — Port some optimizations to flux model family
- **fixed** — Fix ImageUpscaleWithModel crashing on RGBA images
- **changed** — Take the SQLite write lock up front for asset scan and output-registration writes
- **changed** — Move file reads out of the remaining asset write transactions
- **added** — Add ming-image support
- **fixed** — Fix saving and loading ming image model breaking detection
- **changed** — Lower memory usage and add .comfy_attention support for lumina family models
- **fixed** — Fix Qwen VL image preprocessing crash on 4-channel (RGBA) input
- **added** — Add HDR LogC3 and ACEScct to Convert Color Space node

##### What's Changed
* Improve qwen 2.1 KV cache location logic by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16429
* Compile Qwen Image 2.1 transformer blocks by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16430
* Allow model files to contain which attention should be used for each block. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16419
* JsonExtractString can now handle JSON with prefix and/or suffix. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16439
* Remove torchaudio dependency. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16457
* Cuda graphs + memory compiler on ace step 1.5 autoregressive model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16461
* Blend H3 VAE tiles against composited neighbours by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16436
* Fast disk detection to all model loaders. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16425
* [Partner Nodes] feat(Tencent): add Hunyuan Image 3.5 text-to-image and edit nodes by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16462
* Update workflow templates to v0.11.68 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16466
* TextGenerate: Add system_prompt input and separate thinking output (CORE-460) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16442
* MiniMax-H3: Support Fun-Controlnet-Union 2.0 (CORE-462) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16471
* Fix MiniMax-H3 VAE rms_rope crash on offloaded qk_norm_scale by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/16485
* Port some optimizations to flux model family. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16488
* [Partner Nodes] feat(Quiver): add Arrow 2 models with reasoning effort widget by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16478
* [Partner Nodes] feat(Anthropic): add Claude Opus 5.5 to the Claude node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16479
* [Partner Nodes] feat(Recraft): add Recraft V4.1 Flash to the V4 text-to-image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16501
* Update workflow templates to v0.11.69 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16503
* Fix ImageUpscaleWithModel crashing on RGBA images by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/16500
* Take the SQLite write lock up front for asset scan and output-registration writes by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16480
* Move file reads out of the remaining asset write transactions by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16486
* feat: ming-image support by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16482
* Fix saving/loading ming image model breaking detection. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16514
* Lower memory usage and .comfy_attention support for lumina family models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16515
* [Partner Nodes] feat(OpenAI): add GPT-6 Sol and Luna models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16520
* [Partner Nodes] feat(ByteDance): add Seedream 5.0 Flash by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16522
* fix(assets): harden the asset catalogue's failure paths by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16393
* Add missing RDNA2 arches to list. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16537
* feat(npu): support async weight offload streams by @Big2Wheel in https://github.com/Comfy-Org/ComfyUI/pull/16057
* Small fix: skip unnecessary work. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16540
* Fix Qwen VL image preprocessing crash on 4-channel (RGBA) input by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/16548
* [Partner Nodes] feat(ByteDance): add Seedance 2.5 Draft mode by @bigcat88 in https:/

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.38.0]_

### v0.37.0

- Date: 2026-09-21
- Version: v0.37.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.37.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.37.0

- **changed** — Auto-detect and enable --fast-disk when the disk is fast
- **added** — Add transparent background support for GPT Image 2 in Partner Nodes OpenAI
- **added** — Add CFG control to YuE2 Generate Music node
- **changed** — Always put text encoder on GPU when dynamic vram is enabled
- **fixed** — Refuse a P2 run in Tripo whose linked GLB or FBX output would be empty
- **added** — Support MoGe 3
- **changed** — Update default width and height in EmptyLatentImage
- **changed** — Update nodes names and categories
- **added** — Add Qwen3/3.5/3.8 cudagraphs and w4a8 gemv support
- **fixed** — Fix issue with qwen speedup
- **changed** — Lower the pos embed precision of SheetSage2 to match upstream
- **added** — Send Idempotency-Key on partner-proxy calls and collect replays
- **fixed** — Fix ace step VAE decode crashing on non bf16 GPUs
- **added** — Add Qwen-image 2.1 support
- **changed** — Lower wan peak vram when using comfy kitchen attention
- **added** — Add a way to disable fast disk for debugging
- **added** — Add Meshy 7.1 support in Partner Nodes
- **fixed** — Fix MiniMax Music 3 producing noise with CUDA graphs enabled

##### What's Changed
* Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16333
* [Partner Nodes] feat(OpenAI): add transparent background support for GPT Image 2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16366
* Add CFG control to YuE2 Generate Music node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16373
* Always put text encoder on GPU when dynamic vram on. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16374
* [Partner Nodes] fix(Tripo): refuse a P2 run whose linked GLB or FBX output would be empty by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16369
* feat: Support MoGe 3 (CORE-443) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16381
* Update comfy-kitchen version to 0.2.35 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16385
* chores: Update default width and height in EmptyLatentImage by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/16384
* chores: Update nodes names and categories by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/16274
* Qwen3/3.5/3.8 cudagraphs and w4a8 gemv support (CORE-390) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15623
* Fix issue with qwen speedup PR. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16389
* Lower the pos embed precision of SheetSage2 to match upstream. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16395
* [Partner Nodes] feat(client): send Idempotency-Key on partner-proxy calls and collect replays by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16220
* Bump comfyui-frontend-package to 1.53.6 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/16386
* Fix ace step VAE decode crashing on non bf16 GPUs. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16405
* feat: Qwen-image 2.1 support (CORE-423) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16400
* Update embedded docs to v0.5.12 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16396
* Lower wan peak vram when using comfy kitchen attention. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16418
* Update workflow templates to v0.11.65 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16423
* Add a way to disable fast disk for debugging. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16424
* Update workflow templates to v0.11.66 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16426
* [Partner Nodes] feat(Meshy): add Meshy 7.1 support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16412
* Fix MiniMax Music 3 producing noise with CUDA graphs enabled. by @RaynoldVanHeyningen in https://github.com/Comfy-Org/ComfyUI/pull/16428

##### New Contributors
* @RaynoldVanHeyningen made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/16428

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.36.0...v0.37.0

### v0.36.0

- Date: 2026-09-15
- Version: v0.36.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.36.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.36.0

- **added** — Add new model blueprints and reorganize subgraph categories
- **changed** — Bump AMD Windows VA quota to 4TB
- **added** — Add Microsoft mai-image-2.6 models to OpenRouter partner nodes
- **removed** — Drop the dead ROCm triton arch gate
- **added** — Add Gemini 3.8 Flash to the Gemini text node
- **added** — Migrate Tripo to v3 API and add Smart Segment node
- **added** — Add auto aspect ratio to the MAI image node
- **fixed** — Fix h3 fun controlnet with comfy compiler
- **added** — Add linear to ImageColorSpace
- **added** — Implement Video Concatenate node
- **added** — Add Marigold v2 support
- **added** — Support Yue2 music model
- **added** — Add new image edit nodes and Video Eraser node to Bria partner nodes
- **changed** — Consume estimated-duration headers for progress display in client partner nodes
- **changed** — Increase max song duration in Yue2 node
- **fixed** — Don't add noise to the alpha channel in the Add Noise to Image node
- **fixed** — Fix linear_input_act to respect _full_precision_mm fallback
- **fixed** — Fix Yue2 AMD issues and add more controls to the generate ABC node
- **added** — Add Flux Video Edit node to BFL partner nodes
- **added** — Implement Generic Loops

##### What's Changed
* Add new model blueprints and reorganize subgraph categories by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14785
* main: bump the AMD Windows VA quota to 4TB (CORE-409) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16199
* [Partner Noes] feat(OpenRouter): add Microsoft `mai-image-2.6` models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16188
* quant_ops: drop the dead ROCm triton arch gate by @0xDELUXA in https://github.com/Comfy-Org/ComfyUI/pull/16211
* [Partner Nodes] feat(Gemini-LLM): Add Gemini 3.8 Flash to the Gemini text node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16195
* Update instructions for manual install on windows AMD. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16217
* [Partner Nodes] feat(Tripo): migrate to the v3 API, add the Smart Segment node and retire the dead widgets by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16201
* [Partner Nodes] feat(OpenRouter): add auto aspect ratio to the MAI image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16229
* Update workflow templates to v0.11.59 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16233
* Fix h3 fun controlnet with comfy compiler. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16240
* Add linear to ImageColorSpace. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16247
* Implement Video Concatenate (CORE-436) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16267
* fix: Fix unit tests for Concatenate Video node by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/16271
* feat: Marigold v2 support (CORE-431) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16232
* Support Yue2 music model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16250
* Bump comfyui-frontend-package to 1.52.7 by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16275
* [Partner Nodes] feat(Bria): add new image edit nodes and the Video Eraser node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16264
* [Partner Nodes] feat(client): consume estimated-duration headers for progress display by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16152
* Increase max song duration in Yue2 node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16292
* Don't add noise to the alpha channel in the Add Noise to Image node by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15626
* Fix linear_input_act to respect _full_precision_mm fallback by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/16285
* Fix yue2 AMD issues and add more controls to the generate ABC node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16293
* Log typed asset scanner filesystem errors by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16096
* [Partner Nodes] feat(BFL): add the Flux Video Edit node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16259
* Add that Yue 2 is supported to readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16303
* feat(assets): split asset records from content by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16295
* test(assets): keep test typing 3.10-compatible by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/16305
* feat: structured event log lines for the assets system by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/16306
* [Partner Nodes] feat(Gemini-LLM): add GeminiNodeV3, deprecate V2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16287
* Add Marigold V2 and YuE2 blueprints by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16318
* Update workflow templates to v0.11.60 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16319
* Implement Generic Loops (Candidate III - implemented ✅) (CORE-14) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16227

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.36.0]_

### v0.35.0

- Date: 2026-09-09
- Version: v0.35.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.35.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.35.0

- **added** — Support avif format in Save Image Advanced node
- **added** — File3DToMesh node to parse GLB/GLTF/OBJ/STL into MESH
- **added** — cfgpp_ud10_ab sampler
- **added** — VideoTrim and VideoCrop nodes with VIDEO_EDIT widget inputs
- **added** — Support for SenseNova U1.5
- **added** — Live resolution preview widget to ResolutionSelector
- **added** — Comfy Compiler
- **changed** — Recraft V4 Styles and V4 Styles Pro models support
- **changed** — WAN3-Prime model support
- **changed** — Google Omni 1.1 model support
- **changed** — MiniMax-H3 controlnet as a model patch instead of a controlnet
- **changed** — MiniMax-H3 support for H3 Max option and optional VAE
- **changed** — Support for MiniMax-H3 and HiDream O1 loras trained with DiffSynth-Studio / ModelScope
- **changed** — Enable PyTorch SDPA attention and FP8 ops for gfx1170 and gfx1171
- **changed** — Allow disconnected Switch inputs
- **fixed** — Remux HEVC to mp4/mov as hvc1 via hevc_mp4toannexb
- **fixed** — Respect container cgroup memory limit instead of host RAM
- **fixed** — SAM3 segmentation head receiving 4 FPN levels when scalp=1
- **fixed** — Get Image Size Description
- **removed** — Drop retiring Veo 2 and Veo 3.0 models

##### What's Changed
* [Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15883
* [Partner Nodes] feat(Recraft): add V4 Styles by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15903
* [Partner Nodes] feat(WAN): add WAN3-Prime model support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15894
* Bump comfyui-frontend-package to 1.51.9 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15696
* Support avif in Save Image Advanced node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15891
* fix(video): remux HEVC to mp4/mov as hvc1 via hevc_mp4toannexb by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15809
* fix(memory): respect the container cgroup memory limit instead of host RAM (CORE-394) by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15927
* Update workflow templates to v0.11.50 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15931
* [Partner Nodes] feat(Google-Omni): add support for Omni 1.1 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15929
* feat(3d): File3DToMesh node — parse GLB/GLTF/OBJ/STL into MESH by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15919
* Add to readme that we support HDR and high bit depth. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15940
* Add cfgpp_ud10_ab sampler. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15951
* MiniMax-H3: Support PDD LoRA by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15908
* Add section about user input tolerance to AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15955
* [Partner Nodes] fix(HeyGen): update Avatar Video price badge by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15945
* Improve some warning messages. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15977
* feat: add VideoTrim and VideoCrop nodes with VIDEO_EDIT widget inputs by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15637
* Disable push event trigger for failing workflow. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15995
* Add how to cache model stuff to AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16003
* Minimax h3 controlnet as a model patch instead of a controlnet. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15975
* Support SenseNova U1.5 (CORE-411) by @T8mars in https://github.com/Comfy-Org/ComfyUI/pull/15922
* Allow using references with MiniMax-H3 Fun Union and fix prefetch rac… by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/16020
* Disable ck attention when fp32 + low_precision_attention False. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16029
* Enable PyTorch SDPA attention and FP8 ops for gfx1170 by @tvukovic-amd in https://github.com/Comfy-Org/ComfyUI/pull/16014
* [Partner Nodes] feat(MiniMax): add H3 Max option to H3 text-to-video and first-last-frame nodes by @purzbeats in https://github.com/Comfy-Org/ComfyUI/pull/16025
* Update workflow templates to v0.11.52 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16024
* Lower trellis workflow remesh memory usage. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16034
* Annotate temp paths in Preview3DAdvanced / PreviewGaussianSplat / PreviewPointCloud outputs by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/16038
* [Partner Nodes] feat(Minimax-H3): add the Max model to the Reference node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16041
* Update workflow templates to v0.11.54 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/16045
* Fix SAM3 segmentation head receiving 4 FPN levels when scalp=1 by @ussoewwin in https://github.com/Comfy-Org/ComfyUI/pull/15979
* Enable PyTorch SDPA attention and FP8 ops for gfx1171 by @tvukovic-amd in https://github.com/Comfy-Org/ComfyU

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.35.0]_

### v0.34.0

- Date: 2026-08-26
- Version: v0.34.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.34.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.34.0

- **fixed** — Fix minimax music not working on non dynamic vram
- **added** — Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame
- **changed** — Bump comfyui-frontend-package to 1.49.6
- **changed** — Speedup Gemma4 text generation
- **changed** — Update embedded docs to v0.5.10
- **fixed** — Fix thinking handling
- **changed** — Enable dynamic vram by default on ROCm 7.14 and higher
- **added** — Add Seedance 2.5 task_type for video extension to ByteDance partner nodes
- **fixed** — Stop adding an opaque alpha channel to API node images
- **added** — Add Minimax Music 3
- **removed** — Remove custom price extractor logic from x-comfy-credits partner nodes
- **changed** — Allow regular single image Empty Latent Image node to be used with H3
- **removed** — Remove kling-v2 image model from Kling partner nodes
- **changed** — Forward node class attributes into schema for dataset nodes
- **added** — Implement basic FishAudio partner nodes
- **added** — Add 1080p resolution to Seedance 2.5 in ByteDance partner nodes
- **added** — Support per-token video and audio latent noise masks on MiniMax-H3
- **added** — Add support for taeh3
- **added** — Support prompt embeddings for minimax
- **changed** — Keep temp-directory assets visible while their files exist

##### What's Changed
* Fix minimax music not working on non dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15588
* Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15439
* chore(openapi): sync shared API contract from cloud@94d0f1b by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15041
* Bump comfyui-frontend-package to 1.49.6 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15526
* Speedup Gemma4 text generation (CORE-371) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15054
* Update embedded docs to v0.5.10 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15613
* Fix thinking handling by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15611
* Enable dynamic vram by default on ROCm 7.14 and higher. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15633
* [Partner Nodes] feat(ByteDance): add Seedance 2.5 task_type for video extension by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15579
* [Partner Nodes] Stop adding an opaque alpha channel to API node images by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15369
* fix(tests): accept Python 3.14 math error messages by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15645
* Add Minimax Music 3 to readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15656
* [Partner Nodes] feat(x-comfy-credits): remove custom price extractor logic by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15655
* Allow regular single image Empty Latent Image node to be used with H3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15677
* [Partner Nodes] chore(Kling): remove kling-v2 image model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15676
* Forward node class attributes into schema for dataset nodes by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15683
* [Partner Nodes] feat(FishAudio): implement basic nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15612
* [Partner Nodes] feat(ByteDance): add 1080p resolution to Seedance 2.5 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15684
* Update workflow templates to v0.11.43 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15690
* Support per-token video and audio latent noise masks on MiniMax-H3 by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15375
* Add support for taeh3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15695
* feat(minimax): support prompt embeddings by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/15697
* Keep temp-directory assets visible while their files exist by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15510
* Prs/ace graphs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15698
* Drop the duplicate first image from the Qwen-Image-Layered blueprint by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15364
* Add friendly errors to the dynamic vram safetensors loader. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15722
* Fix missing asset preview URLs outside input and output by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15509
* [Partner Nodes] Add Gemini 3.7 Flash to the Gemini text node text node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15688
* Limit Windows multi-GPU visibility (CORE-391) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15737
* [Partner Nodes] chore(Prune): rename Ideogram P-Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15751
* [Partner Nodes] feat(Bytedance): add new Seedream node with Fast Mode widget by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15750
* [Partner Nodes] feat(BFL): add Flux Video Upscale node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15753
* Update workflow templates to v

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.34.0]_

### v0.33.1

- Date: 2026-08-13
- Version: v0.33.1
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.33.1
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.33.1

- **fixed** — Fix KSamplerAdvanced with add_noise disabled on nested latents
- **fixed** — Fix PreviewAny escaping non-ASCII text in dict and list previews
- **fixed** — Fix float64 device in ltx diffusion decoder
- **added** — Support anima tunes with extra blocks
- **changed** — Don't disable dynamic vram on WSL
- **changed** — Query pytorch for aotriton support instead of listing its lib directory
- **fixed** — Fix Generate Text ignoring thinking=false on Gemma4 E2B/E4B
- **changed** — Update comfy-kitchen package version to 0.2.31
- **added** — Add ContextIR and Regenerate To 2K nodes for MiniMax
- **added** — Implement Minimax Music 3 with core support for Cuda Graphs
- **added** — Add GenFill, Eraser, Expand and Increase Resolution nodes for Bria
- **fixed** — Fix llama non-local x path
- **changed** — Update workflow templates to v0.11.41
- **changed** — Minimax early detect qkv vs q,k,v
- **fixed** — Fix minimax music not working on non dynamic vram

##### What's Changed
* Fix KSamplerAdvanced with add_noise disabled on nested latents by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15447
* Update workflow templates to v0.11.40 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15522
* chore: replace api nodes -> partner nodes in README by @robinjhuang in https://github.com/Comfy-Org/ComfyUI/pull/15519
* Fix PreviewAny escaping non-ASCII text in dict and list previews by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15513
* Fix float64 device in ltx diffusion decoder. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15516
* Support anima tunes with extra blocks. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15555
* Don't disable dynamic vram on WSL. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15562
* Query pytorch for aotriton support instead of listing its lib directory by @glop102 in https://github.com/Comfy-Org/ComfyUI/pull/15412
* Fix Generate Text ignoring thinking=false on Gemma4 E2B/E4B by @DrJKL in https://github.com/Comfy-Org/ComfyUI/pull/15278
* Update comfy-kitchen package version to 0.2.31 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15564
* [Partner Nodes] feat(MiniMax): add ContextIR and Regenerate To 2K nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15471
* Implement Minimax Music 3 + Core Support for Cuda Graphs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15570
* [Partner Nodes] feat(Bria): add GenFill, Eraser, Expand and Increase Resolution nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15572
* llama: fix non-local x path by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15580
* Update workflow templates to v0.11.41 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15578
* minimax: early detect qkv vs q,k,v by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15581
* Fix minimax music not working on non dynamic vram. https://github.com/Comfy-Org/ComfyUI/pull/15588

##### New Contributors
* @glop102 made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15412

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.32.0...v0.33.1

### v0.32.0

- Date: 2026-08-11
- Version: v0.32.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.32.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.32.0

- **changed** — Make it easier to debug nested tensors
- **changed** — Update workflow templates to v0.11.39
- **changed** — Minimum officially supported pytorch is now 2.7
- **fixed** — Make Create Layered Image discoverable and its flags self-explanatory
- **fixed** — Fix upscale models breaking on non dynamic vram low vram
- **added** — Add previewable_outputs_count to /api/jobs
- **changed** — Extend ER-SDE noise scaler by scaling h(t)
- **changed** — Make a context manager for cast_bias_weight and use it
- **changed** — Optimize MiniMax-H3 VAE
- **added** — Add Qwen-Image 3.0 Pro support
- **added** — Add tags_all / tags_any / tags_none tag filters to the assets list API
- **fixed** — Fix VAEDecodeTiled crash on NestedTensor latents (MiniMax H3)
- **changed** — Make cu130 warning more visible
- **added** — Implement comfy kitchen attention
- **fixed** — Fix peak memory issue with H3
- **added** — Add support for LTX 2.5
- **added** — Add new nodes for LTX model version 2.5
- **fixed** — Fix for broken tiled audio decode
- **added** — Add Grok-Imagine-Image-2.0 model support
- **fixed** — Fix some clip vision regression

##### What's Changed
* Make it easier to debug nested tensors. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15383
* Update workflow templates to v0.11.37 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15415
* Minimum officially supported pytorch is now 2.7 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15413
* fix: make Create Layered Image discoverable and its flags self-explanatory by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15429
* Fix upscale models breaking on non dynamic vram low vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15437
* Add previewable_outputs_count to /api/jobs (backend half of Media Assets badge fix) by @claude[bot] in https://github.com/Comfy-Org/ComfyUI/pull/15148
* Extend ER-SDE noise scaler by scaling h(t) by @chaObserv in https://github.com/Comfy-Org/ComfyUI/pull/15428
* Make a context manager for cast_bias_weight and use it. by @blepping in https://github.com/Comfy-Org/ComfyUI/pull/14750
* Optimize MiniMax-H3 VAE by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15446
* [Partner Nodes] feat(Qwen): add Qwen-Image 3.0 Pro by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15327
* Add tags_all / tags_any / tags_none tag filters to the assets list API by @synap5e in https://github.com/Comfy-Org/ComfyUI/pull/15332
* Fix VAEDecodeTiled crash on NestedTensor latents (MiniMax H3) by @chelsealong in https://github.com/Comfy-Org/ComfyUI/pull/15477
* Make cu130 warning more visible. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15463
* Implement comfy kitchen attention. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15479
* Fix peak memory issue with H3. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15486
* Add support for LTX 2.5 by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/15499
* [Partner Nodes] feat(LTX): add new nodes for model version 2.5 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15501
* Fix for broken tiled audio decode. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15502
* Update workflow templates to v0.11.39 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15504
* [Partner Nodes] feat(Grok): add Grok-Imagine-Image-2.0 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15496
* Fix some clip vision regression. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15506
* Don't depend on transformers for mistral and llama tokenizers. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15503
* Remove potentially problematic process_tokens method. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15507

##### New Contributors
* @claude[bot] made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15148
* @chelsealong made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15477

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.31.0...v0.32.0

### v0.31.0

- Date: 2026-08-08
- Version: v0.31.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.31.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.31.0

- **changed** — Avoid pinning too much memory on Linux systems with no swap partition
- **fixed** — Cast raw parameters to input device in MiniMax H3 VAEs
- **fixed** — Harden some nodes against potential issues related to combos
- **fixed** — Restore SDPA non-cudnn small attention bypass
- **added** — Add Bloom 2 and Wonder 3.5 models support for TopazAI
- **added** — Add Flux 3 video model support for BFL
- **added** — Support int8_convrot VAE for MiniMax-H3
- **changed** — Speed up LTX and Wan
- **fixed** — Fix MiniMax H3 noise mask sampling
- **deprecated** — Deprecate Reve nodes
- **fixed** — Fix sampler issues for audio with minimax and support more samplers
- **fixed** — Skip creating useless noise in res_multistep sampler
- **added** — Support Wan-Animate2
- **fixed** — Fix full offload on minimax audio VAE
- **added** — Support asym w4a8_int
- **added** — Add SeeDance 2.5 model support for ByteDance
- **added** — Add ImageCompositor node with layer-state compositing and Seedream Layer Separation node
- **fixed** — Fix MiniMax H3 audio corruption with EasyCache

##### What's Changed
* Bump comfyui-frontend-package to 1.47.12 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15244
* Don't pin too much memory on Linux systems with no swap partition. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15266
* fix(minimax): cast raw parameters to input device in H3 VAEs by @rivadart in https://github.com/Comfy-Org/ComfyUI/pull/15268
* Harden some nodes against potential issues related to combos. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15277
* [Partner Nodes] chore(Kling): remove retired legacy models and Virtual Try-On API by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15249
* restore SDPA non-cudnn small attention bypass by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15296
* [Partner Nodes] feat(TopazAI): add Bloom 2 and Wonder 3.5 models support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15294
* [Partner Nodes] feat(BFL): add Flux 3 video model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15295
* Update workflow templates to v0.11.31 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15297
* comfy-aimdo 0.4.12 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15290
* Update the Features section with more up to date stuff. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15302
* Bump comfyui-frontend-package to 1.48.6 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15301
* Make the desktop app more prominent in the readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15330
* Support int8_convrot VAE for MiniMax-H3 by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15334
* Speedup LTX and Wan by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15138
* Fix MiniMax H3 noise mask sampling by @endman100 in https://github.com/Comfy-Org/ComfyUI/pull/15322
* [Partner Nodes] chore(Reve): deprecate Reve nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15331
* Fix sampler issues for audio with minimax, support more samplers. by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15243
* Skip creating useless noise in res_multistep sampler. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15339
* feat: Support Wan-Animate2 (CORE-358) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15362
* chore: fail the CodeRabbit status when the review did not run by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/15382
* Fix full offload on minimax audio vae. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15377
* Update comfy-kitchen package version to 0.2.27 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15388
* [Partner Nodes] chore(Gemini,OpenAI): update pricing for image models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15306
* Fix MiniMax H3 audio corruption with EasyCache by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15390
* Support asym w4a8_int by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15308
* [Partner Nodes] feat(ByteDance): add SeeDance 2.5 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15395
* Bump comfyui-frontend-package to 1.48.7 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15403
* [Partner Nodes] feat: ImageCompositor node with layer-state compositing, layer from bbox and Seedream Layer Separation node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15317
* Update workflow templates to v0.11.34 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15404
* Update comfy-kitchen package version to 0.2.28 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15407

##### New Contributors
* @rivadart made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15268
* @endman100 made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/15322

**Full Changelog**: https://github.com/Comf

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.31.0]_

### v0.30.0

- Date: 2026-08-03
- Version: v0.30.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.30.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.30.0

- **added** — Support int8 convrot embedding lookup
- **added** — Support PrunaVAED faster LTX2.3 decoder
- **added** — Add configurable DETAIL logging side channel
- **added** — Add dataset folder to avoid arbitrary folder access for dataset stuff
- **added** — Add crf option to save video node
- **added** — Support latent previews for nested latents
- **added** — Let the save text node save in csv format
- **added** — Support MiniMax-H3
- **changed** — Load weights to process RAM with MRU policy using pinning infrastructure
- **changed** — Fallback to cudnn attention on linux if flash attention doesn't work
- **changed** — Store mp4 metadata at the beginning of the file when possible
- **changed** — Let the VAEDecodeAudio node decode nested audio
- **changed** — Disable gradients on diffusion models
- **changed** — Expand k, v when attention backend would fall back to math because gqa
- **fixed** — Fix LTXAV crash when sampling without an audio latent
- **fixed** — Fix user.css loading broken by previous changes
- **fixed** — Fix job preview output to prefer media over text
- **fixed** — Fix SVG previews broken by stored-XSS forced-download
- **fixed** — Fix resend cached histogram UI for CurveEditor after page refresh
- **fixed** — Handle case where swap memory query fails on windows

##### What's Changed
* Update comfy-kitchen package version to 0.2.23 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15112
* Support int8 convrot embedding lookup (CORE-371) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15035
* Load weights to process RAM with MRU policy using pinning infrastructure by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15027
* Add configurable DETAIL logging side channel (CORE-369) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15064
* Support PrunaVAED (faster LTX2.3 decoder) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15129
* [Dataset/Security,Feature] Add dataset folder to avoid arbitrary folder access for dataset stuff. by @KohakuBlueleaf in https://github.com/Comfy-Org/ComfyUI/pull/14807
* Fix LTXAV crash when sampling without an audio latent by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15132
* Update comfy-kitchen to fix flux kv issue. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15144
* Fallback to cudnn attention on linux if flash attention doesn't work. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15146
* Fix user.css loading broken by #14734 by @kaalibro in https://github.com/Comfy-Org/ComfyUI/pull/15000
* fix(jobs): prefer media over text for job preview_output by @DeniDoman in https://github.com/Comfy-Org/ComfyUI/pull/14681
* Fix SVG previews broken by the stored-XSS forced-download by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/15149
* Don't enable comfyui_detail.log by default. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15159
* comfy-kitchen AMD support. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15160
* Bump comfyui-frontend-package to 1.47.11 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15161
* [Partner Nodes] adjust pricing for the Bria Video RemoveBackground nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15155
* [Partner Nodes] feat(Ideogram): add new P-Image model support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15154
* Update workflow templates to v0.11.20 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15165
* [Partner Nodes] feat(Minimax): add new MiniMax H3 model support by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15167
* fix: resend cached histogram UI for CurveEditor after page refresh by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/15152
* Don't assume sampler_function has a __name__ attribute in detail logging by @blepping in https://github.com/Comfy-Org/ComfyUI/pull/15179
* [Partner Nodes] chore(Bria): adjust pricing for other video endpoints by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15171
* Delay dynamic pin cleanup until model destruction by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15183
* ops: apply the custom placeholder logic to Linux too by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/15181
* Update workflow templates to v0.11.23 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15187
* [Partner Nodes] fix(ByteDance): encode stereo reference audio without doubling its duration by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15177
* Expand k, v when attention backend would fall back to math because gqa. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15190
* Add crf option to save video node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15191
* Store mp4 metadata at the beginning of the file when possible. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15195
* [Partner Nodes] feat(xAI): update nodes for grok-imagine-video-1.5 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15197
* [Partner Nodes] chore(Bria): increase price for video endpoints by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15186
* Update comfy-kitchen version to 0.2.26 by @

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.30.0]_

### v0.29.2

- Date: 2026-07-31
- Version: v0.29.2
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.29.2
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.29.2

- **fixed** — Fix frontend issues
- **added** — Add new api partner nodes

Frontend fixes and new api/partner nodes.

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.29.0...v0.29.2

### v0.29.0

- Date: 2026-07-29
- Version: v0.29.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.29.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.29.0

- **fixed** — Stream video transcode instead of buffering every frame in RAM
- **added** — Send ComfyUI Job Id in request headers for partner nodes
- **added** — Add JoyImageEdit native model support
- **added** — Add GPT5.6 models for OpenAI partner nodes
- **added** — Add Gemini 3.5 Flash LLM model for Google partner nodes
- **added** — Add HeyGen Avatar, Talking Photo, Create Avatar, Video Translate and TTS nodes
- **added** — Support anima lllite control models
- **added** — Support Gemma4 12B
- **fixed** — Fix gfx1035 not being treated like RDNA2
- **added** — Add video processing nodes and video support for Image Processing Node and trainer
- **added** — Add native Uni3C Controlnet support for Wan models
- **added** — Support MageFlow
- **added** — Allow using float fps for LTXVEmptyLatentAudio
- **changed** — Bump default background usage clamp to 128GB
- **fixed** — Fix Wan dancer issue with batches
- **fixed** — Fix MageFlow on cards that don't support bf16
- **fixed** — Switch Google Omni model to the Interactions API
- **fixed** — Pass videos as inline data for Gemini-Omni
- **deprecated** — Deprecate Runway Gen3a model

##### What's Changed
* fix(Video): stream the video transcode instead of buffering every frame in RAM (CORE-353) (CORE-351) by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14813
* [Partner Nodes] feat(client): send ComfyUI Job Id in request headers by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14934
* Update AGENTS.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14955
* [feat]Add JoyImageEdit native model support by @feice-huang in https://github.com/Comfy-Org/ComfyUI/pull/14428
* [Partner Nodes] feat(OpenAI): add GPT5.6 models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14957
* Various comfy kitchen optimizations and fixes. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14963
* Speed up anima a bit. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14953
* Support anima lllite control models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14954
* [Partner Nodes] feat(Google): add Gemini 3.5 Flash LLM model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14972
* chore(openapi): sync shared API contract from cloud@e964994 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14947
* Update workflow templates to v0.11.11 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14973
* [Partner Nodes] feat(HeyGen): add Avatar, Talking Photo, Create Avatar, Video Translate and TTS nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14958
* More comfy-kitchen int8 optimizations. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14980
* Update workflow templates to v0.11.12 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14986
* [Partner Nodes] fix(Google): switch to the Interactions API for Omni model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14984
* Implement regular and timestep zero reference images to krea 2 for ostris and identity edit ref loras. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14843
* Fix wan dancer issue with batches. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14999
* feat: Support Gemma4 12B (CORE-277) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14304
* Fix gfx1035 not being treated like RDNA2 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15009
* chore: add /AGENTS.md to CODEOWNERS by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14962
* [Trainer,Dataset/Feature] Video processing nodes, Image Processing Node video support, trainer video support (CORE-81) by @KohakuBlueleaf in https://github.com/Comfy-Org/ComfyUI/pull/13588
* FreSca: 5D+ (ex. Anima) fix, model-agnostic iteration by @TheToxin-git in https://github.com/Comfy-Org/ComfyUI/pull/15007
* Add native Uni3C Controlnet support for Wan models (CORE-365) by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/14946
* [Partner Nodes] fix(Gemini-Omni): pass videos as inline data by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15014
* ci: bump cursor-review to github-workflows@964d5aa by @cloud-code-bot[bot] in https://github.com/Comfy-Org/ComfyUI/pull/15017
* Use optimized rms_rope function in joyai image model. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15018
* [Partner Nodes] feat(Openrouter): add new models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15021
* [Partner Nodes] feat(Anthropic): add new models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15023
* Update workflow templates to v0.11.15 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15030
* Make z image/lumina 2 models use comfy kitchen rms rope. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15036
* Bump comfyui-frontend-package to 1.47.10 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15045
* [Partner Nodes] feat(ByteDance): add new audio-1.0-multilingual model by @bigcat88 in https://github.com/Co

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.29.0]_

### v0.28.0

- Date: 2026-07-15
- Version: v0.28.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.28.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.28.0

- **fixed** — Fix Qwen3-VL tokenizer crash with custom embeddings
- **security** — Fix four vulnerabilities (GHSA-779p-m5rp-r4h4)
- **removed** — Remove IdeogramV1 and IdeogramV2 nodes
- **added** — Add support for Seed Audio 1.0
- **removed** — Remove StabilityAI nodes
- **fixed** — Fix error when embedding is loaded with models using llama_template
- **fixed** — Fix bug when setting transparency in color picker
- **security** — Mask authorization headers in logs
- **changed** — Speedup for text model sampling
- **changed** — Skip unloading dynamic model patchers in current workflow
- **fixed** — Fix video crash on videos with undecodable audio streams
- **added** — Implement basic text overlay node
- **changed** — Support gqa on all attention backends and drop support for PyTorch 2.4
- **fixed** — Fix crash when using UNetSelfAttentionMultiply
- **added** — Add models-directory launch argument
- **fixed** — Fix AttributeError in VAE.is_dynamic() for VAEs constructed without a patcher
- **added** — Add Seedream 5 Pro model support
- **added** — Add namespaced model_type tags and align tag semantics
- **fixed** — Fix qwen3vl reference images when used as a text encode models
- **added** — Allow --comfy-api-base target ephemeral testenvs

##### 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/Comfy

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.28.0]_

### v0.27.0

- Date: 2026-06-30
- Version: v0.27.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.27.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.27.0

- **added** — Add support for int8 convrot models
- **added** — Add support for HappyHorse 1.1 model
- **added** — Add 1080p resolution to Grok Image node
- **added** — Add 4K resolution support for SeeDance 2.0
- **added** — Add support for Seed node
- **added** — Add advanced krea 2 model merging node
- **added** — Add bounding box canvas and Ideogram JSON prompt
- **added** — Add support for SeeDance-2.0-Mini video model
- **added** — Add ConditioningMultiply node
- **added** — Add Nano Banana 2 Lite model
- **added** — Add Gemini Video Omni node
- **added** — Make asset hashing opt-in via --enable-asset-hashing flag
- **changed** — Improve int8 performance
- **changed** — Update GLSL node to use ANGLE library
- **fixed** — Fix int8 loras causing lower quality requant with wrong settings
- **fixed** — Fix int8 mm being skipped on offloaded lora weights
- **fixed** — Fix memory leak related to int8
- **changed** — Improve int8 lora applying speed and quality
- **added** — Add int8 support on turing GPUs

The major change in this version is added support for int8 convrot models.

##### What's Changed
* chore(openapi): sync shared API contract from cloud@363764b by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14607
* [Partner Nodes] feat(Alibaba): add support for HappyHorse 1.1 model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14611
* Downgrade the template to 0.10.2 to bring the HH1.1 templates back by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14613
* [Partner Nodes] feat(Grok): add 1080p resolution to Grok Image node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14612
* [Partner Nodes] feat(ByteDance): add 4K resolution support for SeeDance 2.0 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14614
* feat: Add support for Seed node (CORE-295) by @yousef-rafat in https://github.com/Comfy-Org/ComfyUI/pull/14616
* Add advanced krea 2 model merging node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14621
* chore(openapi): sync shared API contract from cloud@42eb0d1 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14619
* feat: Bounding box canvas and Ideogram JSON prompt (CORE-292) by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14537
* [Partner Nodes] feat(ByteDance): add support for SeeDance-2.0-Mini video model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14626
* Update workflow templates to v0.10.7 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14632
* Support int8 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14636
* Faster int8. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14641
* Fix int8 loras causing lower quality requant with wrong settings. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14650
* Update GLSL node to use ANGLE library (CORE-162) by @pythongosssss in https://github.com/Comfy-Org/ComfyUI/pull/13195
* int8 support on turing GPUs. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14662
* ci: add team-gated Cursor review (thin caller for github-workflows) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14527
* Fix int8 mm being skipped on offloaded lora weights. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14669
* Update embedded docs to v0.5.6 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14668
* Better and faster int8 lora applying. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14685
* Bump comfyui-frontend-package to 1.45.20 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14684
* Add ConditioningMultiply node to nodes.py as an addition to other adj… by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/14686
* [Partner Nodes] feat(Google): add Nano Banana 2 Lite model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14693
* Fix memory leak related to int8. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14697
* feat: make asset hashing opt-in via --enable-asset-hashing (off by default) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14663
* [Partner Nodes] feat(Google): add Gemini Video Omni node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14695
* chore: Update nodes categories by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14674
* Update workflow templates to v0.11.1 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14698


**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.26.0...v0.27.0

### v0.26.0

- Date: 2026-06-23
- Version: v0.26.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.26.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.26.0

- **added** — Add checkbox to disable head drawing in node SDPoseDrawKeypoints
- **added** — Support text generation with Qwen3-VL
- **added** — Support SCAIL-2 multireference
- **added** — Support Boogu-Image
- **added** — Add support for Kling V3-Turbo model in Partner Nodes
- **added** — Add enable_telemetry CLI feature flag
- **added** — Add support for Luma Rays 3.2 in Partner Nodes
- **added** — Add Load3DAdvanced node
- **added** — Add jobs-namespace cancel endpoints (POST /api/jobs/{job_id}/cancel, POST /api/jobs/cancel)
- **added** — Support Context Windows sampling with LTX2 models and IC-LoRa guides
- **added** — Add output socket to save nodes
- **added** — Support Krea2
- **changed** — Allow using Qwen3-VL as flux2 klein text encoder
- **changed** — Add negative prompt to boogu edit node and set min images to 0
- **changed** — Update nodes categories
- **changed** — Update TripoSplat nodes categories
- **changed** — Rename a bunch of nodes
- **changed** — Move comfy sys path insert to custom node loading
- **fixed** — Log base directory to startup messages when --base-directory is used
- **fixed** — Respect Retry-After header in Partner Nodes
- **security** — Load training-dataset shards with weights_only=True

##### What's Changed
* chore(openapi): sync shared API contract from cloud@00ef9cc by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14423
* [Partner Nodes] chore(SoniloTextToMusic): reduce price by half by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14500
* Add the checkbox to disable head drawing in node SDPoseDrawKeypoints by @rmarma in https://github.com/Comfy-Org/ComfyUI/pull/14446
* fix: log base directory to startup messages when --base-directory is used by @octo-patch in https://github.com/Comfy-Org/ComfyUI/pull/13370
* feat: Support text generation with Qwen3-VL (CORE-276) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14298
* chore: Update nodes categories (CORE-263) by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14460
* Add new model blueprints by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14506
* docs: add M3 and M4 to Apple Silicon supported chips list by @EXA4V in https://github.com/Comfy-Org/ComfyUI/pull/14449
* Update link to new comfyui desktop repo. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14516
* Update TripoSplat nodes categories by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14512
* feat: SCAIL-2 multireference (CORE-310) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14509
* Allow using Qwen3-VL as flux2 klein text encoder (again) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14526
* feat: Support Boogu-Image (CORE-308) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14523
* Add negative prompt to boogu edit node and set min images to 0. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14529
* [Partner Nodes] feat(Kling): add support for Kling V3-Turbo model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14528
* feat: add enable_telemetry CLI feature flag by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/14530
* Update ComfyUI Desktop to Comfy Desktop for consistent product naming by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14533
* chore(openapi): sync shared API contract from cloud@d10ff72 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14518
* harden: load training-dataset shards with weights_only=True by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14543
* Move comfy sys path insert to custom node loading. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14459
* [Partner Nodes] feat(Luma): add support for Luma Rays 3.2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14540
* [Partner Nodes] fix: respect Retry-After header by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14234
* Bump comfyui-frontend-package to 1.45.19 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14559
* feat: add Load3DAdvanced node by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14316
* Add jobs-namespace cancel endpoints (POST /api/jobs/{job_id}/cancel, POST /api/jobs/cancel) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14493
* feat: Context Windows sampling with LTX2 models and IC-LoRa guides (CORE-3) by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/13325
* Rename a bunch of nodes by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14547
* Small anima optimization. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14557
* chore(openapi): sync shared API contract from cloud@1aea581 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14562
* [Partner Nodes] chore(Google): remove preview versions of models that will be deprecated soon by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14555
* Update extra model paths example. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14570
* Add output socket to save nodes by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/13866
* Update embedded docs to v0.5.5 by @comfyui-wiki in https://github.com/Comfy-O

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.26.0]_

### v0.25.1

- Date: 2026-06-18
- Version: v0.25.1
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.25.1
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.25.1

- **added** — Add support for Kling V3-Turbo model in Partner Nodes

* [Partner Nodes] feat(Kling): add support for Kling V3-Turbo model (https://github.com/Comfy-Org/ComfyUI/pull/14528).

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.25.0...v0.25.1

### v0.25.0

- Date: 2026-06-16
- Version: v0.25.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.25.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.25.0

- **fixed** — Fix image grid bug
- **added** — Allow SaveWEBM node to save with alpha channel
- **added** — Add BriaTransparentVideoBackground node
- **fixed** — Prevent 1080p first/last-frame stretch jump in Seedance 2.0
- **added** — Add Bria Green Background node
- **added** — Add Krea 2 Medium Turbo model
- **added** — Add seed input to Flux Erase node
- **fixed** — Fix ideogram if model dtype gets set to fp8
- **changed** — Consolidate audio nodes into SaveAudioAdvanced node
- **changed** — Enable cfg1 optimization for DualModelGuider with CFGGuider
- **fixed** — Fix interoperation with external source of pinned memory pressure
- **added** — Add new Gemini text node
- **added** — Add temperature and top_p to NanoBanan node
- **added** — Add PreviewGaussianSplat and PreviewPointCloud nodes
- **fixed** — Let Load3D accept output/temp paths and save Preview3DAdvanced to temp/
- **changed** — Reorder Preview3DAdvanced, PreviewGaussianSplat, and PreviewPointCloud inputs and outputs
- **added** — Add Color primitive
- **changed** — Improve ResolutionSelector
- **added** — Extract image dimensions at ingest and emit on asset responses
- **fixed** — Add back apply_rotary_emb for Qwen Image

##### What's Changed
* chore(openapi): sync shared API contract from cloud@7c470f0 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14174
* fix: Image grid bug fix (CORE-215) by @yousef-rafat in https://github.com/Comfy-Org/ComfyUI/pull/14100
* [Partner Nodes] allow SaveWEBM node to save with alpha channel; add BriaTransparentVideoBackground node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14257
* [Partner Nodes] fix (Seedance 2.0): prevent 1080p first/last-frame stretch jump by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14251
* [Partner Nodes] feat: add Bria Green Background node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14277
* [Partner Nodes] feat: add Krea 2 Medium Turbo model by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14280
* [Partner Nodes] feat: add seed input to Flux Erase node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14283
* Update workflow templates to v0.9.98 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14284
* Bump comfyui-frontend-package to 1.45.15 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14265
* Fix ideogram if model dtype gets set to fp8. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14291
* Consolidate audio nodes into SaveAudioAdvanced node (CORE-202) by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/13871
* Enable cfg1 optimization for DualModelGuider with CFGGuider by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14290
* Fix interoperation with external source of pinned memory pressure by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/14252
* Comfy Aimdo 0.4.9 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/14300
* [Partner Nodes] feat: add new Gemini text node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14299
* [Partner Nodes] feat: add temperature and top_p to NanoBanan node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14305
* feat: add PreviewGaussianSplat + PreviewPointCloud nodes by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14194
* Update AMD portable readme. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14303
* BE-1172 fix(3d): let Load3D accept output/temp paths, save Preview3DAdvanced to temp/ by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14294
* feat(3d): reorder Preview3DAdvanced / PreviewGaussianSplat / PreviewPointCloud inputs and outputs by @jtydhr88 in https://github.com/Comfy-Org/ComfyUI/pull/14308
* Update line endings check to ignore .ci files. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14319
* Use windows line endings for windows portable readmes. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14334
* Add SeedVR2 support (CORE-6) by @pollockjj in https://github.com/Comfy-Org/ComfyUI/pull/14110
* Update embedded docs to v0.5.3 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14350
* Add Color primitive by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14260
* Improve ResolutionSelector by @silveroxides in https://github.com/Comfy-Org/ComfyUI/pull/14309
* feat(assets): extract image dimensions at ingest and emit on asset responses by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/13991
* Revert "Add SeedVR2 support (CORE-6)" by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14359
* chore(openapi): sync shared API contract from cloud@5273c30 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14266
* fix: Add back apply_rotary_emb for Qwen Image by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14364
* Allow custom templates with Ideogram4 TE by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14374
* main/server: Add --debug-hang by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/14371
* Add LoRA key mapping for LTXV/LTXAV models by @kelseyee in https://github.com/Comfy-Org/ComfyUI/pull/14349
* fe

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.25.0]_

### v0.24.0

- Date: 2026-06-03
- Version: v0.24.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.24.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.24.0

- **fixed** — Fix cast/dtype issues for the birefnet and dino3 models
- **fixed** — Fix issue with triposplat preview and old offloading mode
- **changed** — Do tripo dinov3 inference in fp32
- **fixed** — Fix uncaught OverflowError in Math Expression node for large int results
- **fixed** — Revert partner nodes category
- **added** — Add Radiance variant support with nonzero txt_ids
- **fixed** — Prevent freeze on manual abort when using MultiGPU CFG Split
- **added** — Add SDXL and QwenImage support to PiD
- **removed** — Remove old useless no comfy kitchen fallback
- **added** — Add Ideogram V4 node support
- **added** — Add Ideogram4 model support
- **deprecated** — Mark DualModelGuider as experimental
- **changed** — Update workflow templates to v0.9.94
- **changed** — Update memory usage factor for ideogram 4 on non dynamic vram

##### What's Changed
* Some cast/dtype fixes for the birefnet and dino3 models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14217
* Fix issue with triposplat preview and old offloading mode. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14218
* Do tripo dinov3 inference in fp32. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14221
* Fix uncaught OverflowError in Math Expression node for large int results by @vidigoat in https://github.com/Comfy-Org/ComfyUI/pull/14214
* fix: Revert partner nodes category by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14229
* Radiance: support variant with nonzero txt_ids by @person4268 in https://github.com/Comfy-Org/ComfyUI/pull/14206
* fix (MultiGPU): prevent freeze on manual abort when using MultiGPU CFG Split by @quasar-of-mikus in https://github.com/Comfy-Org/ComfyUI/pull/14235
* PiD: Add SDXL and QwenImage by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14240
* Remove old useless no comfy kitchen fallback. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14245
* comfy-aimdo: 0.4.8 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/14244
* [Partner Nodes] feat: add Ideogram V4 node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14261
* feat: Add Ideogram4 model support (CORE-208) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14259
* Mark DualModelGuider as experimental by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14262
* Update workflow templates to v0.9.94 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14263
* Memory usage factor for ideogram 4 on non dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14264

##### New Contributors
* @vidigoat made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14214
* @person4268 made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14206
* @quasar-of-mikus made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/14235

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.23.0...v0.24.0

### v0.23.0

- Date: 2026-06-01
- Version: v0.23.0
- Original notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.23.0
- Permalink: https://whatsnew.fyi/product/comfyui/releases/v0.23.0

- **added** — MediaPipe face detection
- **added** — Multi-threaded load of models from disk
- **added** — OAuth 2.1 and RFC 7591 DCR endpoints to OpenAPI
- **added** — And, Or, and Not logic nodes
- **added** — OpenRouter LLM partner node
- **added** — Rodin2.5 partner nodes
- **added** — Microsoft Lens support
- **added** — NVIDIA PixelDiT and PiD support
- **added** — Save Image advanced node
- **added** — MultiGPU work units for accelerated sampling
- **added** — Colored logs
- **changed** — Update MediaPipe nodes to standardize with existing code base
- **changed** — Update MoGe nodes display names, search aliases and descriptions
- **changed** — Move logic nodes into utils category
- **changed** — Lower cache-ram thresholds
- **changed** — Update multigpu to use unet_manual_cast for SelectModelDevice compute dtype
- **fixed** — Correct dimension transposition for single-channel tensors in lanczos
- **fixed** — Fix reshaping lora application
- **fixed** — Fix --use-flash-attention ignored when xformers installed
- **fixed** — Correct description of where compiled FE files live
- **fixed** — Pass correct timesteps to cross-attention AdaLN modulation in LTX AV
- **fixed** — Correct POST /api/assets/import to importPublishedAssets in OpenAPI

##### What's Changed
* feat: MediaPipe face detection (CORE-235) by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/14009
* Multi-threaded load of models from disk (big load time speedups & Offload to disk) (CORE-43,CORE-152,CORE-164,CORE-165,CORE-117) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13802
* Repo security stuff. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14019
* feat(openapi): add OAuth 2.1 + RFC 7591 DCR endpoints by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14026
* fix(openapi): correct POST /api/assets/import to importPublishedAssets by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14027
* openapi: remove cloud-only job_ids query param from GET /api/assets by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14016
* Update MediaPipe nodes to standardize with existing code base (CORE-242) by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14025
* chore: Dataset nodes clean-up (CORE-237) by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14002
* Update MoGe nodes display names, search aliases and descriptions by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14030
* fix(lanczos): correct dimension transposition for single-channel tensors (CORE-228) by @edoardocarmignani in https://github.com/Comfy-Org/ComfyUI/pull/12679
* Fix reshaping lora application by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/14031
* [Partner Nodes] add OpenRouter LLM node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14007
* Update workflow templates to v0.9.82 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14034
* [Partner Nodes] add widget for auto upscaling for the ByteDance2Reference node by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14032
* Add backport release workflow. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14038
* Fix SIGPIPE false negative in Backport Release workflow validation by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/14041
* Add validation for source branch in backport workflow by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14042
* Update backport workflow to use commit SHA input by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14043
* fe: Consolidate warnings spam by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13970
* Update Discord invite link in README.md by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14045
* Adding in And, Or, and Not nodes. by @Pauan in https://github.com/Comfy-Org/ComfyUI/pull/14004
* Move logic nodes into utils category by @alexisrolland in https://github.com/Comfy-Org/ComfyUI/pull/14033
* [Partner Nodes] add new Rodin2.5 nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/14051
* openapi: align response declarations with implementation (5 endpoints) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14058
* Delete the source branch after doing the backport. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14062
* openapi: rename 55 cloud-side operationIds to match runtime (PR A of 3) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14060
* openapi: rename cloud-side response schemas to match runtime (PR D) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14065
* openapi: add enum values + FeedbackRequest schema for cloud cutover (PR E) by @mattmillerai in https://github.com/Comfy-Org/ComfyUI/pull/14070
* Remove dead code. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14072
* Bump comfyui-frontend-package to 1.44.19 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/14074
* Fix --use-flash-attention ignored when xformers installed. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/14083
* fix: correct description of where compiled FE files live by @robinjhuang in https://github.com/Comfy-Org/ComfyUI/pu

_[Truncated at 4000 characters — full notes: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.23.0]_