Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3891 commits
Select commit Hold shift + click to select a range
df22bcd
Support loading the alpha channel of videos. (#13564)
comfyanonymous Apr 26, 2026
7385eb2
Add new ComfyUI blueprints and fix subgraph naming (#13371)
comfyui-wiki Apr 26, 2026
115f418
Make EmptySD3LatentImage node use intermediate dtype. (#13577)
comfyanonymous Apr 27, 2026
6968a70
[Partner Nodes] HappyHorse model (#13582)
bigcat88 Apr 27, 2026
1233f07
chore: update workflow templates to v0.9.63 (#13586)
comfyui-wiki Apr 27, 2026
75143ee
ComfyUI v0.20.0
comfyanonymous Apr 27, 2026
64b8457
ComfyUI v0.20.1 because github is broken again and messed up my release.
comfyanonymous Apr 27, 2026
3cbf015
Read audio and video at the same time in video loader node. (#13591)
comfyanonymous Apr 27, 2026
b47f15f
fix: Handle un-inited meta-tensors in models (fixes a CPU TE crash) (…
rattus128 Apr 28, 2026
ed201ff
ci: dispatch tag push to Comfy-Org/cloud (#13541)
mattmillerai Apr 28, 2026
c0d77a5
Change the `save 3d model` node's filename prefix to `3d/ComfyUI` (CO…
comfyui-wiki Apr 28, 2026
24de8dc
Fix SolidMask and MaskComposite device mismatch with --gpu-only (#13296)
gschreiber Apr 28, 2026
1351993
Handle metadata rotation in pyav code. (#13605)
comfyanonymous Apr 28, 2026
e514119
comfy-aimdo v0.3.0 (#13604)
rattus128 Apr 28, 2026
c7a517c
Make pyav loading code handle tRNS PNG. (#13607)
comfyanonymous Apr 28, 2026
dae3d34
Use pyav to load images instead of pillow. (#13594)
comfyanonymous Apr 28, 2026
fce0398
dynamicVRAM + --cache-ram 2 (CORE-117) (#13603)
rattus128 Apr 28, 2026
0e25a69
Reduce video tiny VAE peak VRAM and decode time (CORE-127) (#13617)
kijai Apr 29, 2026
5eeae3f
Cogvideox (#13402)
Talmaj Apr 29, 2026
a164c82
Add high quality preview support for Flux2 latents (#13496)
blepping Apr 29, 2026
d10fc2d
Lower peak mem usage for 8 bit formats with pyav. (#13626)
comfyanonymous Apr 30, 2026
a7d82ba
Fix SQLAlchemy version format in requirements.txt (#13547)
Kosinkadink Apr 30, 2026
38ecad8
feat(api-nodes): allow custom resolutions for GPTImage2 node (#13631)
bigcat88 Apr 30, 2026
b633244
[Partner Nodes] ByteDance: virtual portrait library for regular image…
bigcat88 Apr 30, 2026
e6e0936
Load other jpeg formats without taking so much memory. (#13642)
comfyanonymous Apr 30, 2026
e9c311b
OneTainer ERNIE LoRA support (#13640)
prookyon Apr 30, 2026
e8e8fee
chore: update workflow templates to v0.9.65 (#13644)
comfyui-wiki May 1, 2026
97f58ba
Add alexisrolland and rattus128 as code owners (#13648)
Kosinkadink May 1, 2026
96f1cee
chore(api-nodes): always display the custom width and height in GPTIm…
bigcat88 May 1, 2026
cf9cbec
Reformat models variable into multiline array CORE-59 (#13513)
Talmaj May 1, 2026
fa75531
chore(api-nodes): remove Moonvalley API nodes (#13659)
bigcat88 May 1, 2026
10b45a7
chore: update workflow templates to v0.9.66 (#13662)
comfyui-wiki May 1, 2026
cf758bd
chore(api-nodes): increase default timeout for partner API node tasks…
bigcat88 May 1, 2026
63103d5
Remove IPEX and clean up checks and add missing synchronize during em…
simonlui May 1, 2026
b5921c8
SDPose: resize fix (#13656)
kijai May 1, 2026
0230e0e
Adding kijai (#13664)
alexisrolland May 1, 2026
67f6cb3
List all the portable downloads in the README section. (#13666)
comfyanonymous May 2, 2026
3e3ed8c
Add script in AMD portable to launch with dynamic vram. (#13667)
comfyanonymous May 2, 2026
783782d
Implement block prefetch + Lora Async load + and adopt in LTX (Speedu…
rattus128 May 2, 2026
ef6722f
Some cleanups to the load image node. (#13677)
comfyanonymous May 3, 2026
1d23a87
chore: update workflow templates to v0.9.68 (#13678)
comfyui-wiki May 3, 2026
f756d80
[Partner Nodes] Topaz Astra 2 model (#13672)
bigcat88 May 3, 2026
be95871
feat: Gemma4 text generation support (CORE-30) (#13376)
kijai May 3, 2026
f6d5068
Update README (#13679)
alexisrolland May 3, 2026
b5bb83c
Fix issue blend images with alpha (#13615)
alexisrolland May 3, 2026
d0f0b15
Update ComfyUI screenshot in README (#13683)
alexisrolland May 3, 2026
867b8d2
fix: gracefully handle port-in-use error on server startup (#13001)
luke-mino-altherr May 3, 2026
025e679
Batch broadcasting in JoinImageWithAlpha node (#13686)
kijai May 3, 2026
b138133
Enable triton comfy kitchen via cli-arg (#12730)
silveroxides May 3, 2026
cea8d09
Refactor LoadImageMask to use LoadImage code. (#13687)
comfyanonymous May 3, 2026
2806163
Default control_after_generate to fixed in PrimitiveInt node (#13690)
Kosinkadink May 3, 2026
5538f62
fix: Update ColorTransfer node ref_image to be mandatory (#13691)
alexisrolland May 4, 2026
f3ea976
Fix a1111 typo in extra_model_paths.yaml (#2720)
soof-golan May 4, 2026
c33d26c
fix: Proper memory estimation for frame interpolation when not using …
kijai May 4, 2026
c47633f
prefetch: guard against no offload (#13703)
rattus128 May 4, 2026
1ac7818
make control-net load order deterministic (#13701)
rattus128 May 4, 2026
1265955
ops: handle multi-compute of the same weight (#13705)
rattus128 May 4, 2026
15a4494
chore: Update display names and categories (CORE-151) (#13693)
alexisrolland May 5, 2026
35819e3
fix(spec): mark DeviceStats.index and NodeInfo.essentials_category as…
mattmillerai May 5, 2026
413e250
spec: add workflow_id / workflow_version_id to PromptRequest with x-r…
mattmillerai May 5, 2026
ae457da
feat: add generic --feature-flag CLI arg and --list-feature-flags reg…
Kosinkadink May 5, 2026
e758594
Add deploy environment header (Comfy-Env) to partner node API calls (…
Kosinkadink May 5, 2026
9aef025
Document core release frequency is now ~2 weeks. (#13710)
comfyanonymous May 5, 2026
fed8d5e
feat: Auto-regressive video generation (CORE-25) (#13082)
Talmaj May 5, 2026
8d75211
fix: SplitImageToTileList and ImageMergeTileList to use tile_height f…
alvinttang May 5, 2026
c55ff85
feat(api-nodes): add Luma UNI-1 models (#13614)
bigcat88 May 5, 2026
6917bce
[Partner Nodes] add Gpt 5.5 and 5.5-pro LLM models (#13673)
bigcat88 May 5, 2026
d794b62
Update workflow templates to v0.9.69 (#13714)
comfyui-wiki May 5, 2026
639f631
chore: Update display names and categories for text nodes (CORE-155) …
alexisrolland May 5, 2026
ea6880b
Fix Content-Disposition header missing 'attachment;' prefix (#13093)
themachinehf May 5, 2026
41d73ad
fix(audio): drop sample_rate key from LTXVEmptyLatentAudio (CORE-157)…
drozbay May 5, 2026
1ac60da
Add Spectral lint CI gate for openapi.yaml (#13410)
mattmillerai May 5, 2026
431fadb
fix(api-io): serialize MultiCombo multi_select as object config (#13484)
Kosinkadink May 5, 2026
8901479
feat: add cloud-specific fields to OSS openapi.yaml as nullable (#13623)
mattmillerai May 5, 2026
1655f80
Add temporal_downscale_ratio to LatentFormat (#13702)
drozbay May 5, 2026
e5369c0
feat: Context windows - add causal_window_fix to improve blending of …
drozbay May 5, 2026
c168960
First step of supporting save filenames without trailing _ (#13722)
comfyanonymous May 6, 2026
160b95f
Update language options in nodes_ace.py (#12578)
iChristGit May 6, 2026
2b63add
fix: return millisecond timestamps from get_file_info() (#12996)
luke-mino-altherr May 6, 2026
78b3096
Void model - pass 1 & 2 (CORE-38) (#13403)
Talmaj May 6, 2026
9c34f5f
Bump comfyui-frontend-package to 1.43.17 (#13723)
comfy-pr-bot May 6, 2026
6bcd8b9
Revert "Fix Content-Disposition header missing 'attachment;' prefix (…
guill May 6, 2026
cd8c7a2
Throttle dynamic VRAM prepare logging (#13704)
kijai May 7, 2026
e35348a
Add .comfy_environment to portable. (#13746)
comfyanonymous May 7, 2026
1b25f12
[Partner Nodes] add grok-imagine-image-quality model (#13725)
bigcat88 May 7, 2026
25757a5
chore: update workflow templates to v0.9.72 (#13732)
comfyui-wiki May 7, 2026
c945a43
fix(api-nodes): fixed price badge for Kling V3 model in the Motion Co…
bigcat88 May 7, 2026
c011fb5
[Partner Nodes] new NanoBanana2 node with DynamicCombo/Autogrow (#13…
bigcat88 May 7, 2026
8dc3f3f
Improve SAM3 large input handling (#13767)
kijai May 8, 2026
ef8f256
Add I2V for causal forcing model. (#13719)
Talmaj May 8, 2026
df7bf1d
Update warning message for ComfyUI frontend installation. (#13796)
comfyanonymous May 8, 2026
c867354
fix: make NodeReplaceManager.register() idempotent (#13596)
Kosinkadink May 8, 2026
594de37
Update nodes categories and display names (CORE-89) (#13786)
alexisrolland May 8, 2026
56c7409
[Partner Nodes] use "adaptive" aspect ratio for SD2 nodes (#13800)
bigcat88 May 8, 2026
bac6fc3
Fix typos (#10986)
omahs May 8, 2026
d3c18c1
Add support for BiRefNet background remove model (CORE-46) (#12747)
yousef-rafat May 8, 2026
05cd076
fix: Make LTXVAddGuide center-crop guide images to match other LTXV n…
drozbay May 8, 2026
9864f5a
fix: Stop LTXVImgToVideoInplace from mutating input latents and dropp…
drozbay May 8, 2026
c5ecd23
fix: Fix bug when mask not on same device (CORE-181) (#13801)
alexisrolland May 8, 2026
87878f3
Add cloud-runtime FE-facing operations to spec (#13734)
mattmillerai May 8, 2026
6504573
[Partner Nodes] additionally use Baidu server to detect the accessibi…
bigcat88 May 8, 2026
66669b2
I don't think there was any because nobody complained. (#13807)
comfyanonymous May 9, 2026
4e82343
Add cloud-runtime experiment node-schema endpoints to spec (#13806)
mattmillerai May 9, 2026
8b08bfd
Add description field to blueprint subgraphs (#13797)
lin-bot23 May 9, 2026
7bbf1e8
[Partner Nodes] Tripo3D 3.1 model (#13788)
bigcat88 May 9, 2026
a4b7e3b
Bump comfyui-frontend-package to 1.43.18 (#13809)
comfy-pr-bot May 9, 2026
3200f28
Support Wan-Dancer (#13813)
kijai May 9, 2026
20f5e47
Use LatentCutToBatch instead. (#13815)
comfyanonymous May 9, 2026
95f6652
Add Boolean support to Math Expression Node (#13224)
LaVie024 May 10, 2026
aa9d2fc
chore: update workflow templates to v0.9.73 (#13822)
comfyui-wiki May 10, 2026
1eeaf23
Remove advanced flag from layers input in EmptyQwenImageLayeredLatent…
comfyui-wiki May 10, 2026
dabfe73
Add New Blueprints (#13570)
comfyui-wiki May 10, 2026
f505cb4
chore: remove extra word in comment (#13826)
box4wangjing May 11, 2026
52976f3
ComfyUI v0.21.0
comfyanonymous May 11, 2026
b565dc7
[Partner Nodes] new Flux2ImageNode and GrokImageEditNodeV2 nodes with…
bigcat88 May 11, 2026
46063aa
[Partner Nodes] new ByteDanceSeedreamNodeV2 node with DynamicCombo an…
bigcat88 May 11, 2026
428c323
[Partner Nodes] new OpenAI Image node with DynamicCombo and Autogrow …
bigcat88 May 11, 2026
20e4394
model_patcher: Fix safetensors saving of fp8 (#13835)
rattus128 May 11, 2026
0a7d2ff
Support anima TE lora kohya format. (#13847)
comfyanonymous May 12, 2026
8e53f00
feat: Support HiDream-O1-Image (CORE-187) (#13817)
kijai May 12, 2026
0155ddc
Fix dtype issue with hidream o1 (#13849)
comfyanonymous May 12, 2026
c9589f2
[Partner Nodes] fix Quiver nodes (#13851)
bigcat88 May 12, 2026
fb097be
Mark deprecated cloud-runtime endpoints in spec (#13789)
mattmillerai May 12, 2026
a5f7bc5
Suppress false-positive Spectral lint on WebSocket endpoint (#13842)
mattmillerai May 12, 2026
1d95ed2
Fix LTXV mid-video multi-frame guide alignment (CORE-129) (#13625)
drozbay May 12, 2026
300b6c8
Revert some breaking changes. (#13861)
comfyanonymous May 13, 2026
cccb697
fix: create input directory if missing in LoadAudio define_schema (#1…
angad777 May 13, 2026
2bd65f2
Better Hidream O1 mem usage factor for non dynamic vram. (#13864)
comfyanonymous May 13, 2026
240363f
chore: update embedded docs to v0.5.0 (#13865)
comfyui-wiki May 13, 2026
a5189fe
Add Create Video to the essentials tab (#13863)
AustinMroz May 13, 2026
8505abf
feat: Extend Save3D to save vertex colors and textures (CORE-189) (#1…
kijai May 13, 2026
b94941d
[Partner Nodes] add Claude LLM node (#13867)
bigcat88 May 13, 2026
afb4fa1
chore: update workflow templates to v0.9.75 (#13877)
comfyui-wiki May 13, 2026
74c17a2
Fix void failing with RuntimeError: start (0) + length (464) exceeds …
Talmaj May 13, 2026
26515ac
ComfyUI v0.21.1
comfyanonymous May 13, 2026
fb51a98
Add test that each model has unique identifiers CORE-134 (#13654)
Talmaj May 14, 2026
1f28908
Make audio processing nodes handle None -inputs (#13879)
kijai May 14, 2026
3d870ff
chore: update workflow templates to v0.9.77 (#13895)
comfyui-wiki May 14, 2026
3f9bdc7
Add careers link to README and startup log (#13897)
robinjhuang May 14, 2026
7a063e8
Remove annoying message. (#13899)
comfyanonymous May 14, 2026
4f60189
Include workflow_id in all execution WebSocket messages (CORE-198) (#…
christian-byrne May 14, 2026
616cab4
Revert "Include workflow_id in all execution WebSocket messages (CORE…
comfyanonymous May 14, 2026
ed78da0
Create SECURITY.md. (#13902)
comfyanonymous May 14, 2026
b112f68
Generalize frontend version warning to all comfy* requirements.txt en…
christian-byrne May 14, 2026
b200002
Persists ModelNoiseScale when also patching shift (#13892)
kijai May 15, 2026
77e2ed5
feat: Support MoGe (CORE-168) (#13878)
kijai May 15, 2026
04856ac
Allow negative `batch_index` on `ImageFromBatch` and `LatentFromBatch…
drozbay May 15, 2026
33ce449
Reduce LTX2.3 peak VRAM when guide_mask is in use (CORE-166) (#13735)
kijai May 15, 2026
5d5a455
Remove useless option and clarify what lowvram does. (#13922)
comfyanonymous May 16, 2026
d3607a8
feat: Add downscaled IC-LoRA support to LTXVAddGuide (CORE-102) (#13896)
drozbay May 16, 2026
7c4d95d
Enhance README with application and cloud links (#13936)
comfyanonymous May 17, 2026
f48d2a0
Log which quant ops are enabled/emulated. (#13946)
comfyanonymous May 17, 2026
aeadb7a
correct OOM format (#13950)
Apophis3158 May 18, 2026
b39af21
Fix Qwen3.5 text generation with multiple input images (#13943)
kijai May 18, 2026
971c9e3
HiDream-O1: support area conditioning (#13944)
kijai May 18, 2026
264b003
[Partner Nodes] fix Opus 4.7 sending deprecated temperature parameter…
bigcat88 May 18, 2026
d4c6c9e
fix(FeatherMask): correct negative zero indexing for right/bottom fea…
alvinttang May 18, 2026
16f862f
implement dynamic clip saving (#13959)
rattus128 May 18, 2026
164a9d4
[Partner Nodes] add ByteDance Seed LLM node (#13919)
bigcat88 May 18, 2026
187e523
Fix BiRefNet issue (#13966)
yousef-rafat May 18, 2026
292814c
feat: Add optional attention_mask input to LTXVAddGuide (CORE-220) (#…
drozbay May 18, 2026
df2454b
Reduce min for Batch Image/Mask/Latent nodes from 2 to 1 (#13721)
Kosinkadink May 19, 2026
990a7ae
Initial work to make downscale_ratio_temporal work. (#13972)
comfyanonymous May 19, 2026
d71cc1c
chore: Various QoL updates of nodes display names, descriptions and c…
alexisrolland May 19, 2026
a4382e0
Use temporal downscale to make empty audio latent nodes more reusable…
comfyanonymous May 19, 2026
6b61918
docs(openapi): deprecate /api/upload/mask in favor of /api/upload/ima…
mattmillerai May 19, 2026
d0328b4
docs(openapi): remove top-level width/height fields on Asset schema (…
mattmillerai May 19, 2026
626b082
Fix typo in ops.py (#11925)
NAM-MAN May 19, 2026
cc4d711
feat(openapi): add optional description field to workspace API key sc…
mattmillerai May 19, 2026
6887165
docs(openapi): tighten workspace API key description field (BE-1004) …
mattmillerai May 19, 2026
7ec7b6f
Adding new StringFormat node (#13997)
Pauan May 20, 2026
72e3f60
Add downscale ratio to empty ltxv latent. (#13999)
comfyanonymous May 20, 2026
78b5dec
fix: Hunyuan3D 2.1 batch size crashes in attention and forward pass (…
Kivylius May 20, 2026
f9c84c9
Support Stable Audio 3 model. (#14010)
comfyanonymous May 20, 2026
4efe1dd
chore: update workflow templates to v0.9.79 (#14011)
comfyui-wiki May 20, 2026
a8d2519
ComfyUI v0.22.0
comfyanonymous May 20, 2026
4d6a058
feat: MediaPipe face detection (CORE-235) (#14009)
kijai May 20, 2026
5aa5ccc
Multi-threaded load of models from disk (big load time speedups & Off…
rattus128 May 21, 2026
95fdc6c
Repo security stuff. (#14019)
comfyanonymous May 21, 2026
9f9b32e
feat: add OAuth 2.1 + RFC 7591 DCR endpoints to openapi.yaml (#14026)
mattmillerai May 21, 2026
ea174d3
fix(openapi): correct POST /api/assets/import to importPublishedAsset…
mattmillerai May 21, 2026
1668aaf
openapi: remove cloud-only job_ids query param from GET /api/assets (…
mattmillerai May 21, 2026
7b7c5fe
Update MediaPipe nodes to standardize with existing code base (CORE-2…
alexisrolland May 21, 2026
af3d9b6
chore: Dataset nodes clean-up (CORE-237) (#14002)
alexisrolland May 21, 2026
4259a0c
Update MoGe nodes display names, search aliases and descriptions (#14…
alexisrolland May 21, 2026
aab41a9
fix(lanczos): correct dimension transposition for single-channel tens…
edoardocarmignani May 21, 2026
03e5118
Fix reshaping lora application (#14031)
rattus128 May 21, 2026
6ecf5ec
[Partner Nodes] add OpenRouter LLM node (#14007)
bigcat88 May 21, 2026
2ca1480
chore: update workflow templates to v0.9.82 (#14034)
comfyui-wiki May 21, 2026
b293f8c
[Partner Nodes] add widget for automatic upscaling for the ByteDance2…
bigcat88 May 21, 2026
32e5839
Add backport release workflow. (#14038)
comfyanonymous May 21, 2026
5d681a5
Fix SIGPIPE false negative in backport release validation (#14041)
Kosinkadink May 21, 2026
8fecef0
Add validation for source branch in backport workflow (#14042)
comfyanonymous May 21, 2026
8edff54
Update backport workflow to use commit SHA input (#14043)
comfyanonymous May 22, 2026
f48c328
fe: Consolidate warnings (#13970)
rattus128 May 22, 2026
9650570
Update Discord invite link in README.md (#14045)
comfyanonymous May 22, 2026
38ebc19
Adding in And, Or, and Not nodes. (#14004)
Pauan May 22, 2026
93888ae
Move logic nodes into utils category (#14033)
alexisrolland May 22, 2026
1579bbb
[Partner Nodes] add new Rodin2.5 nodes (#14051)
bigcat88 May 22, 2026
112fcd5
openapi: align response declarations with implementation (5 endpoints…
mattmillerai May 22, 2026
e75b739
Delete the source branch after doing the backport. (#14062)
comfyanonymous May 22, 2026
7984a6a
openapi: rename 55 cloud-side operationIds to match runtime (PR A of …
mattmillerai May 22, 2026
c3c881f
openapi: rename cloud-side response schemas to match runtime (PR D) (…
mattmillerai May 22, 2026
187442c
openapi: add enum values + FeedbackRequest schema for cloud cutover (…
mattmillerai May 23, 2026
d80fcaf
Remove dead code. (#14072)
comfyanonymous May 23, 2026
0af1230
Bump comfyui-frontend-package to 1.44.19 (#14074)
comfy-pr-bot May 24, 2026
08d809d
Fix --use-flash-attention ignored when xformers installed. (#14083)
comfyanonymous May 24, 2026
32a7092
fix: correct description of where compiled FE files live (#14013)
robinjhuang May 24, 2026
ea62dc1
openapi: fix invalid BillingStatus schema (object + enum hybrid) (#14…
mattmillerai May 24, 2026
39f963b
mark loads to pins as cold immediately (#14088)
rattus128 May 24, 2026
b30e980
cache-ram: lower thresholds (#14089)
rattus128 May 24, 2026
63bcaec
Add colored logs (#14036)
Talmaj May 25, 2026
0077d78
Save Image advanced node (CORE-32) (#13850)
comfyanonymous May 25, 2026
a4141a0
chore: update embedded docs to v0.5.1 (#14101)
comfyui-wiki May 25, 2026
6de7fc0
Emit `hash` alongside `asset_hash` on all Asset responses (#13739)
mattmillerai May 25, 2026
04879a8
Add new open-source model and built-in tool blueprints (#13980)
comfyui-wiki May 25, 2026
0a2dd86
MultiGPU Work Units For Accelerated Sampling (CORE-184) (#7063)
Kosinkadink May 26, 2026
da49b7d
Remove useless annotations imports. (#14105)
comfyanonymous May 26, 2026
88956e7
multigpu: use unet_manual_cast for SelectModelDevice compute dtype (#…
Kosinkadink May 26, 2026
57414da
fix: cross-attention AdaLN scale, shift, sigma parameters calculation…
izorinLightricks May 26, 2026
41812fa
feat: Microsoft Lens support (CORE-248) (#14077)
kijai May 26, 2026
f9f54ca
Lens: some cleanup (#14112)
kijai May 26, 2026
9217757
openapi: document QueueManageResponse body on POST /api/queue (#14117)
mattmillerai May 26, 2026
28f4ef2
feat: Support NVIDIA PixelDiT and PiD (CORE-201) (#14103)
kijai May 27, 2026
d8d860a
Closer memory usage factors for PID (#14123)
comfyanonymous May 27, 2026
e75a92c
Add memory usage factor for lens model. (#14124)
comfyanonymous May 27, 2026
2072d3e
fix: Stop LTXVCropGuides leaving stray latent frames when guides shar…
drozbay May 27, 2026
0cce76d
[Partner Nodes] feat: improve video references uploading for SeeDance…
bigcat88 May 27, 2026
53eba22
chore: update workflow templates to v0.9.85 (#14134)
comfyui-wiki May 27, 2026
175e854
[Partner Nodes] feat: add Krea2 nodes (#14130)
bigcat88 May 27, 2026
b1cba6f
convert nodes_lt_upsampler nodes to V3 schema (#12423)
bigcat88 May 27, 2026
51ef17e
[Partner Nodes] feat: Beeble SwitchX nodes (#14137)
bigcat88 May 27, 2026
987a937
Support context window for PiD and fix lq_latent rounding (#14136)
kijai May 27, 2026
85a403d
Disable sage attention in stable audio dit and VAE. (#14148)
comfyanonymous May 28, 2026
174208d
chore: Update nodes categories (#14145)
alexisrolland May 28, 2026
8ed308b
feat: add camera intrinsics fields to Load3DCamera info (#14143)
jtydhr88 May 28, 2026
be06873
Make Load3D model_file optional by adding "none" choice (#13379)
jtydhr88 May 28, 2026
4af9a47
[Partner Nodes] fix: add runtime check for SeeDance2 image inputs (#1…
bigcat88 May 28, 2026
cffa2f4
[Partner Nodes] chore: update the category of the Beeble nodes (#14156)
bigcat88 May 28, 2026
6ceec29
feat: add overwrite/increment to SaveImageTextDataSetToFolderNode (#1…
zeerd May 28, 2026
6dd3c67
Add unreviewed merge detector for SOC 2 compliance (#14146)
luke-mino-altherr May 28, 2026
bcf805a
Bump pyav package to fix some image loading issues. (#14160)
comfyanonymous May 29, 2026
26aad73
refactor: drop rotation from Load3DCamera (#14159)
jtydhr88 May 29, 2026
ade4dfd
Update and pin comfy-kitchen version to 0.2.9 (#14161)
comfyanonymous May 29, 2026
6842961
float: use CK stochastic rounding cuda kernel (#13971)
rattus128 May 29, 2026
b10a616
chore: update workflow templates to v0.9.91 (#14163)
comfyui-wiki May 29, 2026
e7214d7
feat: add model_info output to Load3D node (#14144)
jtydhr88 May 29, 2026
ea5b092
[Partner Nodes] fix: removed "beta" models versions from Grok nodes (…
bigcat88 May 29, 2026
54d5be4
Fix background removal mask output shape (#14171)
kijai May 29, 2026
ec1896a
[Partner Nodes] feat: add new nodes for Tripo3D P1 model (#14155)
bigcat88 May 29, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  

This file was deleted.

133 changes: 116 additions & 17 deletions .ci/update_windows/update.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
import pygit2
from datetime import datetime
import sys
import os
import shutil
import filecmp

def pull(repo, remote_name='origin', branch='master'):
for remote in repo.remotes:
Expand All @@ -25,41 +28,137 @@ def pull(repo, remote_name='origin', branch='master'):

if repo.index.conflicts is not None:
for conflict in repo.index.conflicts:
print('Conflicts found in:', conflict[0].path)
print('Conflicts found in:', conflict[0].path) # noqa: T201
raise AssertionError('Conflicts, ahhhhh!!')

user = repo.default_signature
tree = repo.index.write_tree()
commit = repo.create_commit('HEAD',
user,
user,
'Merge!',
tree,
[repo.head.target, remote_master_id])
repo.create_commit('HEAD',
user,
user,
'Merge!',
tree,
[repo.head.target, remote_master_id])
# We need to do this or git CLI will think we are still merging.
repo.state_cleanup()
else:
raise AssertionError('Unknown merge analysis result')

pygit2.option(pygit2.GIT_OPT_SET_OWNER_VALIDATION, 0)
repo = pygit2.Repository(str(sys.argv[1]))
repo_path = str(sys.argv[1])
repo = pygit2.Repository(repo_path)
ident = pygit2.Signature('comfyui', 'comfy@ui')
try:
print("stashing current changes")
print("stashing current changes") # noqa: T201
repo.stash(ident)
except KeyError:
print("nothing to stash")
print("nothing to stash") # noqa: T201
except:
print("Could not stash, cleaning index and trying again.") # noqa: T201
repo.state_cleanup()
repo.index.read_tree(repo.head.peel().tree)
repo.index.write()
try:
repo.stash(ident)
except KeyError:
print("nothing to stash.") # noqa: T201

backup_branch_name = 'backup_branch_{}'.format(datetime.today().strftime('%Y-%m-%d_%H_%M_%S'))
print("creating backup branch: {}".format(backup_branch_name))
repo.branches.local.create(backup_branch_name, repo.head.peel())
print("creating backup branch: {}".format(backup_branch_name)) # noqa: T201
try:
repo.branches.local.create(backup_branch_name, repo.head.peel())
except:
pass

print("checking out master branch")
print("checking out master branch") # noqa: T201
branch = repo.lookup_branch('master')
ref = repo.lookup_reference(branch.name)
repo.checkout(ref)
if branch is None:
try:
ref = repo.lookup_reference('refs/remotes/origin/master')
except:
print("fetching.") # noqa: T201
for remote in repo.remotes:
if remote.name == "origin":
remote.fetch()
ref = repo.lookup_reference('refs/remotes/origin/master')
repo.checkout(ref)
branch = repo.lookup_branch('master')
if branch is None:
repo.create_branch('master', repo.get(ref.target))
else:
ref = repo.lookup_reference(branch.name)
repo.checkout(ref)

print("pulling latest changes")
print("pulling latest changes") # noqa: T201
pull(repo)

print("Done!")
if "--stable" in sys.argv:
def latest_tag(repo):
versions = []
for k in repo.references:
try:
prefix = "refs/tags/v"
if k.startswith(prefix):
version = list(map(int, k[len(prefix):].split(".")))
versions.append((version[0] * 10000000000 + version[1] * 100000 + version[2], k))
except:
pass
versions.sort()
if len(versions) > 0:
return versions[-1][1]
return None
latest_tag = latest_tag(repo)
if latest_tag is not None:
repo.checkout(latest_tag)

print("Done!") # noqa: T201

self_update = True
if len(sys.argv) > 2:
self_update = '--skip_self_update' not in sys.argv

update_py_path = os.path.realpath(__file__)
repo_update_py_path = os.path.join(repo_path, ".ci/update_windows/update.py")

cur_path = os.path.dirname(update_py_path)


req_path = os.path.join(cur_path, "current_requirements.txt")
repo_req_path = os.path.join(repo_path, "requirements.txt")


def files_equal(file1, file2):
try:
return filecmp.cmp(file1, file2, shallow=False)
except:
return False

def file_size(f):
try:
return os.path.getsize(f)
except:
return 0


if self_update and not files_equal(update_py_path, repo_update_py_path) and file_size(repo_update_py_path) > 10:
shutil.copy(repo_update_py_path, os.path.join(cur_path, "update_new.py"))
exit()

if not os.path.exists(req_path) or not files_equal(repo_req_path, req_path):
import subprocess
try:
subprocess.check_call([sys.executable, '-s', '-m', 'pip', 'install', '-r', repo_req_path])
shutil.copy(repo_req_path, req_path)
except:
pass


stable_update_script = os.path.join(repo_path, ".ci/update_windows/update_comfyui_stable.bat")
stable_update_script_to = os.path.join(cur_path, "update_comfyui_stable.bat")

try:
if not file_size(stable_update_script_to) > 10:
shutil.copy(stable_update_script, stable_update_script_to)
except:
pass

8 changes: 7 additions & 1 deletion .ci/update_windows/update_comfyui.bat
Original file line number Diff line number Diff line change
@@ -1,2 +1,8 @@
@echo off
..\python_embeded\python.exe .\update.py ..\ComfyUI\
pause
if exist update_new.py (
move /y update_new.py update.py
echo Running updater again since it got updated.
..\python_embeded\python.exe .\update.py ..\ComfyUI\ --skip_self_update
)
if "%~1"=="" pause
3 changes: 0 additions & 3 deletions .ci/update_windows/update_comfyui_and_python_dependencies.bat

This file was deleted.

8 changes: 8 additions & 0 deletions .ci/update_windows/update_comfyui_stable.bat
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
@echo off
..\python_embeded\python.exe .\update.py ..\ComfyUI\ --stable
if exist update_new.py (
move /y update_new.py update.py
echo Running updater again since it got updated.
..\python_embeded\python.exe .\update.py ..\ComfyUI\ --skip_self_update --stable
)
if "%~1"=="" pause

This file was deleted.

28 changes: 28 additions & 0 deletions .ci/windows_amd_base_files/README_VERY_IMPORTANT.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
As of the time of writing this you need this driver for best results:
https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-7-1-1.html

HOW TO RUN:

If you have a AMD gpu:

run_amd_gpu.bat

If you have memory issues you can try disabling the smart memory management by running comfyui with:

run_amd_gpu_disable_smart_memory.bat

IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints

You can download the stable diffusion XL one from: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors


RECOMMENDED WAY TO UPDATE:
To update the ComfyUI code: update\update_comfyui.bat


TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.



Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --use-pytorch-cross-attention
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --enable-dynamic-vram
pause
2 changes: 2 additions & 0 deletions .ci/windows_intel_base_files/run_intel_gpu.bat
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
pause
2 changes: 2 additions & 0 deletions .ci/windows_nightly_base_files/run_nvidia_gpu_fast.bat
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast
pause
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,9 @@ if you have a NVIDIA gpu:

run_nvidia_gpu.bat

if you want to enable the fast fp16 accumulation (faster for fp16 models with slightly less quality):

run_nvidia_gpu_fast_fp16_accumulation.bat


To run it in slow CPU mode:
Expand All @@ -14,7 +17,7 @@ run_cpu.bat

IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints

You can download the stable diffusion 1.5 one from: https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt
You can download the stable diffusion 1.5 one from: https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/blob/main/v1-5-pruned-emaonly-fp16.safetensors


RECOMMENDED WAY TO UPDATE:
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
..\python_embeded\python.exe -s ..\ComfyUI\main.py --windows-standalone-build --disable-api-nodes
echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
pause
3 changes: 3 additions & 0 deletions .ci/windows_nvidia_base_files/run_nvidia_gpu.bat
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
pause
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast fp16_accumulation
echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
pause
Loading