Comfy-Org/ComfyUI v0.23.0 on GitHub

What's Changed

feat: MediaPipe face detection (CORE-235) by @kijai in #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 #13802
Repo security stuff. by @comfyanonymous in #14019
feat(openapi): add OAuth 2.1 + RFC 7591 DCR endpoints by @mattmillerai in #14026
fix(openapi): correct POST /api/assets/import to importPublishedAssets by @mattmillerai in #14027
openapi: remove cloud-only job_ids query param from GET /api/assets by @mattmillerai in #14016
Update MediaPipe nodes to standardize with existing code base (CORE-242) by @alexisrolland in #14025
chore: Dataset nodes clean-up (CORE-237) by @alexisrolland in #14002
Update MoGe nodes display names, search aliases and descriptions by @alexisrolland in #14030
fix(lanczos): correct dimension transposition for single-channel tensors (CORE-228) by @edoardocarmignani in #12679
Fix reshaping lora application by @rattus128 in #14031
[Partner Nodes] add OpenRouter LLM node by @bigcat88 in #14007
Update workflow templates to v0.9.82 by @comfyui-wiki in #14034
[Partner Nodes] add widget for auto upscaling for the ByteDance2Reference node by @bigcat88 in #14032
Add backport release workflow. by @comfyanonymous in #14038
Fix SIGPIPE false negative in Backport Release workflow validation by @Kosinkadink in #14041
Add validation for source branch in backport workflow by @comfyanonymous in #14042
Update backport workflow to use commit SHA input by @comfyanonymous in #14043
fe: Consolidate warnings spam by @rattus128 in #13970
Update Discord invite link in README.md by @comfyanonymous in #14045
Adding in And, Or, and Not nodes. by @Pauan in #14004
Move logic nodes into utils category by @alexisrolland in #14033
[Partner Nodes] add new Rodin2.5 nodes by @bigcat88 in #14051
openapi: align response declarations with implementation (5 endpoints) by @mattmillerai in #14058
Delete the source branch after doing the backport. by @comfyanonymous in #14062
openapi: rename 55 cloud-side operationIds to match runtime (PR A of 3) by @mattmillerai in #14060
openapi: rename cloud-side response schemas to match runtime (PR D) by @mattmillerai in #14065
openapi: add enum values + FeedbackRequest schema for cloud cutover (PR E) by @mattmillerai in #14070
Remove dead code. by @comfyanonymous in #14072
Bump comfyui-frontend-package to 1.44.19 by @comfy-pr-bot in #14074
Fix --use-flash-attention ignored when xformers installed. by @comfyanonymous in #14083
fix: correct description of where compiled FE files live by @robinjhuang in #14013
openapi: fix invalid BillingStatus schema (object + enum hybrid) by @mattmillerai in #14071
Aimdo 0.4.5 + Cold marking of pins by @rattus128 in #14088
cache-ram: lower thresholds by @rattus128 in #14089
Add colored logs by @Talmaj in #14036
Save Image advanced node (CORE-32) by @comfyanonymous in #13850
Update embedded docs to v0.5.1 by @comfyui-wiki in #14101
Emit hash alongside asset_hash on all Asset responses by @mattmillerai in #13739
Add new open-source model and built-in tool blueprints by @comfyui-wiki in #13980
MultiGPU Work Units For Accelerated Sampling (CORE-184) by @Kosinkadink in #7063
Remove some useless annotations imports. by @comfyanonymous in #14105
multigpu: use unet_manual_cast for SelectModelDevice compute dtype by @Kosinkadink in #14108
fix(LTX AV): pass correct timesteps to cross-attention AdaLN modulation by @izorinLightricks in #14097
feat: Microsoft Lens support (CORE-248) by @kijai in #14077
Lens: some cleanup by @kijai in #14112
openapi: document QueueManageResponse body on POST /api/queue by @mattmillerai in #14117
feat: Support NVIDIA PixelDiT and PiD (CORE-201) by @kijai in #14103
Closer memory usage factors for PID by @comfyanonymous in #14123
Add memory usage factor for lens model. by @comfyanonymous in #14124
fix: Stop LTXVCropGuides leaving stray latent frames when guides share a start position (CORE-206) by @drozbay in #13882
[Partner Nodes] feat: improve video references uploading for SeeDance 2 by @bigcat88 in #14098
Update workflow templates to v0.9.85 by @comfyui-wiki in #14134
[Partner Nodes] feat: add Krea2 Image nodes by @bigcat88 in #14130
[V3] convert nodes_lt_upsampler nodes to V3 schema by @bigcat88 in #12423
[Partner Nodes] feat: Beeble SwitchX nodes by @bigcat88 in #14137
Support context window for PiD and fix lq_latent rounding by @kijai in #14136
Disable sage attention in stable audio dit and VAE. by @comfyanonymous in #14148
chore: Update nodes categories by @alexisrolland in #14145
feat: add camera intrinsics fields to Load3DCamera info by @jtydhr88 in #14143
Make Load3D model_file optional by adding "none" choice by @jtydhr88 in #13379
[Partner Nodes] fix: add runtime check for SeeDance2 image inputs by @bigcat88 in #14152
[Partner Nodes] chore: update the category of the Beeble nodes by @bigcat88 in #14156
feat: add overwrite/increment to SaveImageTextDataSetToFolderNode by @zeerd in #13215
Add unreviewed merge detector for SOC 2 compliance by @luke-mino-altherr in #14146
Bump pyav package to fix some image loading issues. by @comfyanonymous in #14160
refactor: drop rotation from Load3DCamera by @jtydhr88 in #14159
Update and pin comfy-kitchen version to 0.2.9 by @comfyanonymous in #14161
float: use CK stochastic rounding cuda kernel (CORE-200) by @rattus128 in #13971
Update workflow templates to v0.9.91 by @comfyui-wiki in #14163
feat: add model_info output to Load3D node by @jtydhr88 in #14144
[Partner Nodes] fix: removed "beta" models versions from Grok nodes by @bigcat88 in #14170
Fix background removal mask output shape by @kijai in #14171
[Partner Nodes] feat: add new nodes for Tripo3D P1 model by @bigcat88 in #14155
Remove useless code. by @comfyanonymous in #14178
Speed up anima a bit on nvidia. by @comfyanonymous in #14181
feat(io): add File3DPLY / File3DSPLAT / File3DSPZ / File3DKSPLAT types by @jtydhr88 in #14185
Threaded Loader performance fixes / improvements (+ Aimdo 0.4.6) by @rattus128 in #14116
Revert deprecation of non-dynamic smart memory (CORE-152 (revert)) by @rattus128 in #14183
feat: add Preview3DAdvanced node by @jtydhr88 in #14175
Update embedded docs to v0.5.2 by @comfyui-wiki in #14193
Speed up ernie model by a bit on nvidia and use higher quality rope. by @comfyanonymous in #14192
fix: enable XPU MultiGPU CFG Split on Windows (CFG > 1) by @savvadesogle in #14191
feat: Add gaussian splat nodes by @kijai in #14190
[Partner Nodes] added grok-imagine-video-1.5 model to the GrokVideo node in First Frame mode by @bigcat88 in #14198
Remove old portable updater migration code. by @comfyanonymous in #14202
feat: Add TripoSplat support by @kijai in #14210
[Partner Nodes] feat: add Flux Virtual Try-On and Erase nodes by @bigcat88 in #14207
Update workflow templates to v0.9.92 by @comfyui-wiki in #14212
[Partner Nodes] fix: respect VideoSlice trim when resizing videos by @bigcat88 in #14213

New Contributors

@edoardocarmignani made their first contribution in #12679
@zeerd made their first contribution in #13215
@savvadesogle made their first contribution in #14191

Full Changelog: v0.22.0...v0.23.0