Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4492 commits
Select commit Hold shift + click to select a range
b53e247
rename comfy/logging.py to comfy/internal_logging.py (#15231)
olifre Aug 2, 2026
57500fc
feat: Support MiniMax-H3 (CORE-375) (#15224)
kijai Aug 3, 2026
f72b688
Update workflow templates to v0.11.26 (#15228)
comfyui-wiki Aug 3, 2026
6eba773
chore: update workflow templates to v0.11.27 (#15239)
comfyui-wiki Aug 3, 2026
b1693ec
ComfyUI v0.30.0
comfyanonymous Aug 3, 2026
14b0522
Bump comfyui-frontend-package to 1.47.12 (#15244)
comfy-pr-bot Aug 3, 2026
e377e26
Don't pin too much memory on Linux systems with no swap partition. (#…
comfyanonymous Aug 3, 2026
16e3f30
fix(minimax): cast raw parameters to input device in H3 VAEs (#15268)
rivadart Aug 3, 2026
9a9fdb1
Harden some nodes against potential issues related to combos. (#15277)
comfyanonymous Aug 4, 2026
c44dea1
[Partner Nodes] chore(Kling): remove retired legacy models and Virtua…
bigcat88 Aug 4, 2026
40dbdc1
restore SDPA non-cudnn small attention bypass (#15296)
rattus128 Aug 4, 2026
1868372
[Partner Nodes] feat(TopazAI): add Bloom 2 and Wonder 3.5 models supp…
bigcat88 Aug 4, 2026
e7970cb
[Partner Nodes] feat(BFL): add Flux 3 video model (#15295)
bigcat88 Aug 5, 2026
2bbb200
chore: update workflow templates to v0.11.31 (#15297)
comfyui-wiki Aug 5, 2026
ba1d0ef
comfy-aimdo 0.4.13 (#15290)
rattus128 Aug 5, 2026
de23a54
Update the Features section with more up to date stuff. (#15302)
comfyanonymous Aug 5, 2026
6f7cd7f
Bump comfyui-frontend-package to 1.48.6 (#15301)
comfy-pr-bot Aug 5, 2026
7972b5b
Make the desktop app more prominent in the readme. (#15330)
comfyanonymous Aug 5, 2026
bbda836
Support int8_convrot VAE (#15334)
kijai Aug 6, 2026
15989f8
Speedup LTX and Wan (#15138)
kijai Aug 6, 2026
563b98e
Fix MiniMax H3 latent noise mask sampling (#15322)
endman100 Aug 6, 2026
2eb6097
[Partner Nodes] chore(Reve): deprecate Reve nodes (#15331)
bigcat88 Aug 6, 2026
bdcb886
Fix sampler issues for audio with minimax, support more samplers. (#1…
kijai Aug 6, 2026
88fec4b
Skip creating useless noise in res_multistep sampler. (#15339)
comfyanonymous Aug 6, 2026
a464ac3
feat: Support Wan-Animate2 (CORE-358) (#15362)
kijai Aug 7, 2026
0dd9b15
chore: fail the CodeRabbit status when the review did not run (#15382)
christian-byrne Aug 7, 2026
2340099
Fix full offload on minimax audio vae. (#15377)
comfyanonymous Aug 7, 2026
0ab8332
Update comfy-kitchen package version to 0.2.27 (#15388)
comfyanonymous Aug 7, 2026
531ea7d
[Partner Nodes] chore(Gemini,OpenAI): update pricing for image models…
bigcat88 Aug 7, 2026
93cb5ed
Fix audio carry to wrappers (#15390)
kijai Aug 7, 2026
344b439
Support asym w4a8_int (#15308)
kijai Aug 7, 2026
0db8694
[Partner Nodes] feat(ByteDance): add SeeDance 2.5 model (#15395)
bigcat88 Aug 7, 2026
6db4fa2
Bump comfyui-frontend-package to 1.48.7 (#15403)
comfy-pr-bot Aug 7, 2026
8fadc7b
[Partner Nodes] feat: ImageCompositor node with layer-state compositi…
jtydhr88 Aug 7, 2026
2f40b71
chore: update workflow templates to v0.11.34 (#15404)
comfyui-wiki Aug 7, 2026
66057c4
Update comfy-kitchen package version to 0.2.28 (#15407)
comfyanonymous Aug 7, 2026
43cb4ff
ComfyUI v0.31.0
comfyanonymous Aug 7, 2026
cd84f47
Make it easier to debug nested tensors. (#15383)
comfyanonymous Aug 8, 2026
5599a05
chore: update workflow templates to v0.11.37 (#15415)
comfyui-wiki Aug 8, 2026
dd79c64
Minimum officially supported pytorch is now 2.7 (#15413)
comfyanonymous Aug 8, 2026
00d02f2
fix: make Create Layered Image discoverable and its flags self-explan…
jtydhr88 Aug 8, 2026
9eaba63
Fix upscale models breaking on non dynamic vram low vram. (#15437)
comfyanonymous Aug 8, 2026
a683fa6
Add previewable_outputs_count to /api/jobs (backend half of Media Ass…
claude[bot] Aug 9, 2026
40e46c7
Extend ER-SDE noise scaler by scaling h(t) (#15428)
chaObserv Aug 9, 2026
cbbc9da
Make a context manager for cast_bias_weight and use it. (#14750)
blepping Aug 9, 2026
2a68ce3
Optimize MiniMax-H3 VAE (#15446)
kijai Aug 9, 2026
7d11ec3
[Partner Nodes] feat(Qwen): add Qwen-Image 3.0 image generation and e…
bigcat88 Aug 10, 2026
34744cd
Add tags_all / tags_any / tags_none tag filters to the assets list AP…
synap5e Aug 10, 2026
6233790
Fix VAEDecodeTiled crash on NestedTensor latents (MiniMax H3) (#15477)
chelsealong Aug 11, 2026
4f3544d
Make cu130 warning more visible. (#15463)
comfyanonymous Aug 11, 2026
bf4c9a0
Implement comfy kitchen attention. (#15479)
comfyanonymous Aug 11, 2026
62b3c94
Fix peak memory issue with H3. (#15486)
comfyanonymous Aug 11, 2026
57ce8e1
Add support for LTX 2.5 (#15499)
alexisrolland Aug 11, 2026
ce4fc13
[Partner Nodes] feat(LTX): add new nodes for model version 2.5 (#15501)
bigcat88 Aug 11, 2026
2a19bbf
Fix for broken tiled audio decode. (#15502)
comfyanonymous Aug 11, 2026
eb4a7b4
chore: update workflow templates to v0.11.39 (#15504)
comfyui-wiki Aug 11, 2026
2eaf09f
[Partner Nodes] feat(Grok): add Grok Imagine Image 2.0 model (#15496)
bigcat88 Aug 11, 2026
d9f9d2b
Fix some clip vision regression. (#15506)
comfyanonymous Aug 11, 2026
bbb4b04
Don't depend on transformers for mistral and llama tokenizers. (#15503)
comfyanonymous Aug 11, 2026
024cbc5
Remove potentially problematic process_tokens method. (#15507)
comfyanonymous Aug 11, 2026
c2bcbec
ComfyUI v0.32.0
comfyanonymous Aug 11, 2026
27bca65
Fix KSamplerAdvanced with add_noise disabled on nested latents (#15447)
kijai Aug 11, 2026
1108f2a
chore: update workflow templates to v0.11.40 (#15522)
comfyui-wiki Aug 12, 2026
945ffca
chore: replace api nodes -> partner nodes in README (#15519)
robinjhuang Aug 12, 2026
26d7f85
Fix PreviewAny escaping non-ASCII text in dict and list previews (#15…
christian-byrne Aug 12, 2026
bd34f33
Fix float64 device in ltx diffusion decoder. (#15516)
comfyanonymous Aug 12, 2026
725e6ec
Support anima tunes with extra blocks. (#15555)
comfyanonymous Aug 12, 2026
6b30dc2
Don't disable dynamic vram on WSL. (#15562)
comfyanonymous Aug 13, 2026
2220d11
Query pytorch for aotriton support instead of listing its lib directo…
glop102 Aug 13, 2026
addd479
Fix Generate Text ignoring thinking=false on Gemma4 E2B/E4B (#15278)
DrJKL Aug 13, 2026
b323a34
Update comfy-kitchen package version to 0.2.31 (#15564)
comfyanonymous Aug 13, 2026
1266698
[Partner Nodes] feat(MiniMax): add ContextIR and Regenerate nodes (#1…
bigcat88 Aug 13, 2026
efd4e95
Implement Minimax Music 3 + Core Support for Cuda Graphs (#15570)
rattus128 Aug 13, 2026
e535e59
[Partner Nodes] feat(Bria): add GenFill, Eraser, Expand and Increase …
bigcat88 Aug 13, 2026
af3d215
llama: fix non-local x path (#15580)
rattus128 Aug 13, 2026
86aedfd
chore: update workflow templates to v0.11.41 (#15578)
comfyui-wiki Aug 13, 2026
ddbaa87
minimax: early detect qkv vs q,k,v (#15581)
rattus128 Aug 13, 2026
2f35f4a
ComfyUI v0.33.0
comfyanonymous Aug 13, 2026
03fa4e4
Fix minimax music not working on non dynamic vram. (#15588)
comfyanonymous Aug 13, 2026
e01fb4c
Add MiniMaxH3AddGuide for anchoring image and audio guides at any fra…
drozbay Aug 13, 2026
8f37cf8
chore(openapi): sync shared API contract from cloud@94d0f1b (#15041)
comfy-pr-bot Aug 13, 2026
a779de4
Bump comfyui-frontend-package to 1.49.6 (#15526)
comfy-pr-bot Aug 13, 2026
7fe8a61
Speedup Gemma4 text generation (CORE-371) (#15054)
kijai Aug 14, 2026
1c6d8d4
chore: update embedded docs to v0.5.10 (#15613)
comfyui-wiki Aug 14, 2026
55b6a9b
Fix thinking handling (#15611)
kijai Aug 14, 2026
a736507
Enable dynamic vram by default on ROCm 7.14 and higher. (#15633)
comfyanonymous Aug 15, 2026
0f1fa67
[Partner Nodes] feat(ByteDance): add Seedance 2.5 task_type for video…
bigcat88 Aug 15, 2026
a9ab2b6
[Partner Nodes] Stop adding an opaque alpha channel to API node image…
christian-byrne Aug 15, 2026
37ac9ff
fix(tests): accept Python 3.14 math error messages (#15645)
bigcat88 Aug 15, 2026
aaabf34
Add MiniMax Music 3 to readme. (#15656)
comfyanonymous Aug 15, 2026
b963f4a
[Partner Nodes] feat(x-comfy-credits): remove custom price extractor …
bigcat88 Aug 16, 2026
0696f61
Allow regular single image Empty Latent Image node to be used with H3…
comfyanonymous Aug 17, 2026
784462c
Remove kling-v2 from Kling Image Generation node (#15676)
bigcat88 Aug 17, 2026
0d80858
Forward node class attributes into schema for dataset nodes (#15683)
christian-byrne Aug 17, 2026
7d39997
[Partner Nodes] feat(FishAudio): implement basic nodes (#15612)
bigcat88 Aug 17, 2026
edd2ddb
[Partner Nodes] feat(ByteDance): add 1080p resolution to Seedance 2.5…
bigcat88 Aug 17, 2026
c173938
chore: update workflow templates to v0.11.43 (#15690)
comfyui-wiki Aug 17, 2026
ff6c8a8
Support per-token video and audio latent noise masks on MiniMax-H3 (#…
drozbay Aug 18, 2026
8e869ef
Add support for taeh3. (#15695)
comfyanonymous Aug 18, 2026
e5a38e3
feat(minimax): support prompt embeddings (#15697)
silveroxides Aug 18, 2026
cc0fc21
Keep temp-directory assets visible while their files exist (#15510)
synap5e Aug 18, 2026
8b2d291
Prs/ace graphs (#15698)
rattus128 Aug 18, 2026
187eda8
Drop the duplicate first image from the Qwen-Image-Layered blueprint …
christian-byrne Aug 19, 2026
a3e5cce
Add friendly errors to the dynamic vram safetensors loader. (#15722)
comfyanonymous Aug 19, 2026
3aba3da
Derive asset preview URLs from the file path (#15509)
synap5e Aug 19, 2026
c67885b
[Partner Nodes] feat(Gemini-LLM): Add Gemini 3.7 Flash to the Gemini …
bigcat88 Aug 19, 2026
5ab2f7a
Limit Windows multi-GPU visibility (#15737)
rattus128 Aug 19, 2026
4f244e5
[Partner Nodes] chore(Prune): rename Ideogram P-Image node (#15751)
bigcat88 Aug 20, 2026
18c9aa4
[Partner Nodes] feat(Bytedance): add new Seedream node with Fast Mode…
bigcat88 Aug 20, 2026
d336365
[Partner Nodes] feat(BFL): add Flux Video Upscale node (#15753)
bigcat88 Aug 20, 2026
8583b0c
chore: update workflow templates to v0.11.44 (#15754)
comfyui-wiki Aug 20, 2026
de6b062
ci: add Notify on Merge dispatch workflow (#15568)
luke-mino-altherr Aug 20, 2026
dcbcf8c
Support HDR video saving, AV1 codec, mkv and webm. (#15741)
comfyanonymous Aug 20, 2026
76135e5
Add HDR color space options to h264 codec in Save Video node. (#15764)
comfyanonymous Aug 21, 2026
28864ca
fix: fail CLA allowlist step on API errors (#15792)
alexisrolland Aug 21, 2026
0e65cb9
feat: Support Pixal3d and TRELLIS2 (CORE-278) (CORE-199) (CORE-236) (…
kijai Aug 22, 2026
7dde561
Increase trellis2 memory factor a bit. (#15796)
comfyanonymous Aug 22, 2026
783545f
[Partner Nodes] feat(ByteDance): add vCube Video Enhance node (#15755)
bigcat88 Aug 22, 2026
924743a
Minimax-H3: Add missing special tokens (#15808)
kijai Aug 22, 2026
9db05e0
Add colorspace option and change bit_depth to a combo on CreateVideo.…
comfyanonymous Aug 23, 2026
3422dfd
Default Windows to the first CUDA device (#15813)
rattus128 Aug 23, 2026
82f839f
feat: Support Sam3d-body (CORE-35) (#14370)
kijai Aug 23, 2026
b78cec8
Increase minimum pyav version. (#15827)
comfyanonymous Aug 23, 2026
41218e4
[Partner Nodes] feat(Wan): add Wan 3.0 video generation nodes (#15843)
bigcat88 Aug 24, 2026
bab6ee5
[Partner Nodes] feat(Meshy): add Meshy-7 support (#15807)
bigcat88 Aug 24, 2026
180060c
chore: update workflow templates to v0.11.46 (#15864)
comfyui-wiki Aug 24, 2026
eb8cad7
Update nodes_image_compare.py (#15868)
alexisrolland Aug 24, 2026
5f0c4e1
Fix default database path for custom user directory (#14539)
Constantine1916 Aug 24, 2026
2618d32
Python 3.10 will be EOL soon, please upgrade. (#15874)
comfyanonymous Aug 25, 2026
a1079ba
[Partner Nodes] chore(Tripo): remove retired Refine node and v2.0 mod…
bigcat88 Aug 25, 2026
7a054eb
comfy-aimdo 0.4.15 (#15886)
rattus128 Aug 25, 2026
7d9d0c3
[Partner Nodes] feat(Pixverse): add Pixverse V6 model support (#15880)
bigcat88 Aug 25, 2026
ef0d752
Update workflow templates to v0.11.48 (#15888)
comfyui-wiki Aug 25, 2026
12d5279
ComfyUI v0.34.0
comfyanonymous Aug 25, 2026
b133e48
[Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models…
bigcat88 Aug 26, 2026
30d03fe
[Partner Nodes] feat(Recraft): add V4 Styles (#15903)
bigcat88 Aug 26, 2026
a25c7bf
[Partner Nodes] feat(WAN): add WAN3-Prime model support (#15894)
bigcat88 Aug 26, 2026
40b9898
Bump comfyui-frontend-package to 1.51.9 (#15696)
comfy-pr-bot Aug 26, 2026
5653b4a
Support avif in Save Image Advanced node. (#15891)
comfyanonymous Aug 26, 2026
d8e7bbc
fix(video): remux HEVC to mp4/mov as hvc1 via hevc_mp4toannexb (#15809)
bigcat88 Aug 27, 2026
7773972
fix(memory): respect the container cgroup memory limit instead of hos…
bigcat88 Aug 27, 2026
e20d433
chore: update workflow templates to v0.11.50 (#15931)
comfyui-wiki Aug 27, 2026
4c6359f
[Partner Nodes] feat(Google-Omni): add support for Omni 1.1 model (#1…
bigcat88 Aug 27, 2026
a255b96
feat(3d): File3DToMesh node — parse GLB/GLTF/OBJ/STL into MESH (#15919)
jtydhr88 Aug 28, 2026
0a33ed6
Add to readme that we support HDR and high bit depth. (#15940)
comfyanonymous Aug 28, 2026
3ac5d79
Add cfgpp_ud10_ab sampler. (#15951)
comfyanonymous Aug 28, 2026
2504e68
MiniMax-H3: Support PDD LoRA (#15908)
kijai Aug 28, 2026
e7051b0
Add section about user input tolerance to AGENTS.md (#15955)
comfyanonymous Aug 29, 2026
5bdcb5f
[Partner Nodes] fix(HeyGen): update Avatar Video price badge (#15945)
bigcat88 Aug 29, 2026
8a33128
Improve some warning messages. (#15977)
comfyanonymous Aug 30, 2026
f938505
feat: add VideoTrim and VideoCrop nodes with VIDEO_EDIT widget inputs…
jtydhr88 Aug 30, 2026
95d755c
Disable push event trigger for failing workflow. (#15995)
comfyanonymous Aug 31, 2026
a8b4fa6
Add how to cache model stuff to AGENTS.md (#16003)
comfyanonymous Aug 31, 2026
d3eaf6a
Minimax h3 controlnet as a model patch instead of a controlnet. (#15975)
comfyanonymous Aug 31, 2026
3216c62
Support SenseNova U1.5 (CORE-411) (#15922)
T8mars Sep 1, 2026
02aa707
Allow using references with MiniMax-H3 Fun Union and fix prefetch rac…
kijai Sep 1, 2026
3258eb3
Disable ck attention when fp32 + low_precision_attention False. (#16029)
comfyanonymous Sep 1, 2026
cf7aedc
Enable PyTorch SDPA attention and FP8 ops for gfx1170 (#16014)
tvukovic-amd Sep 2, 2026
624f565
[Partner Nodes] feat(MiniMax): add H3 Max option to H3 text-to-video …
purzbeats Sep 2, 2026
03468f4
chore: update workflow templates to v0.11.52 (#16024)
comfyui-wiki Sep 2, 2026
4e024cb
Lower trellis workflow remesh memory usage. (#16034)
comfyanonymous Sep 2, 2026
ace9172
Annotate temp paths in Preview3DAdvanced / PreviewGaussianSplat / Pre…
jtydhr88 Sep 2, 2026
ec803fc
[Partner Nodes] feat(Minimax-H3): add the Max model to the Reference …
bigcat88 Sep 2, 2026
a87667f
chore: update workflow templates to v0.11.54 (#16045)
comfyui-wiki Sep 2, 2026
2035799
Fix SAM3 segmentation head receiving 4 FPN levels when scalp=1 (#15979)
ussoewwin Sep 2, 2026
13d2580
Enable PyTorch SDPA attention and FP8 ops for gfx1171 (#16039)
tvukovic-amd Sep 2, 2026
5672751
Add live resolution preview widget to ResolutionSelector (#16013)
jtydhr88 Sep 2, 2026
1af040b
Emit the document canvas from ImageCompositor for the layer editor (#…
jtydhr88 Sep 3, 2026
345c919
Add warning about forcing single GPU mode on Windows (#16055)
comfyanonymous Sep 3, 2026
30bdda1
Register partner_run_gate_enabled feature flag (#16012)
MaanilVerma Sep 3, 2026
5f05631
Update README.md (#16071)
alexisrolland Sep 3, 2026
1aec3a1
MiniMax-H3: Make VAE optional, allow using text encoder only referenc…
kijai Sep 3, 2026
d22a13c
Support MiniMax-H3 and HiDream O1 loras trained with DiffSynth-Studio…
yjy415 Sep 3, 2026
9c90340
Update nodes to improve search rank (#16074)
alexisrolland Sep 3, 2026
0eb098b
Lower peak trellis workflow vram and ram usage. (#16054)
comfyanonymous Sep 3, 2026
d9726bb
Make comfyui handle missing workflow media properly. (#16079)
comfyanonymous Sep 4, 2026
1c68191
Remove some workflow media from portable install to make it smaller. …
comfyanonymous Sep 4, 2026
e80c157
[Partner Nodes] feat(Recraft): add V4 Styles Pro models to Create Sty…
bigcat88 Sep 4, 2026
a12b28a
Fix Get Image Size description (#16091)
rattus128 Sep 4, 2026
31dfbd4
Allow disconnected Switch inputs (#16083)
rattus128 Sep 4, 2026
e3a78da
chore: Update nodes categories (#16077)
alexisrolland Sep 4, 2026
804eb55
Introduce Comfy Compiler (CORE-389) (#15861)
rattus128 Sep 4, 2026
5c23fb7
Remove now unnecessary minimax memory workaround. (#16103)
comfyanonymous Sep 4, 2026
8f486ad
[Partner Nodes] fix(Tripo): real output formats, exact pricing, missi…
bigcat88 Sep 4, 2026
6c53f8c
[Partner Nodes] feat(Meta): add Muse Image nodes (#16078)
purzbeats Sep 4, 2026
3c282ce
[Partner Nodes] feat(Anthropic): add Claude Fable 5.1 to the Claude n…
bigcat88 Sep 4, 2026
5efd057
[Partner Nodes] feat(MiniMax): add H3 Max Turbo option to H3 text-to-…
bigcat88 Sep 4, 2026
acb2a01
chore: update workflow templates to v0.11.55 (#16104)
comfyui-wiki Sep 4, 2026
6e3c0bd
comfy-aimdo 0.5.2 (#16108)
rattus128 Sep 4, 2026
250b2e9
[Partner Nodes] feat(Comfy-Cloud): add nodes that run curated workflo…
deepme987 Sep 5, 2026
8a43c6b
[Partner Nodes] feat(OpenAI): add gpt 6 astra model and reasoning par…
bigcat88 Sep 5, 2026
f00bfd6
[Partner Nodes] deprecate retired models (#16121)
bigcat88 Sep 5, 2026
18ebc2a
Update comfy-kitchen version to 0.2.33 (#16133)
comfyanonymous Sep 5, 2026
d1c5e64
Fix potential mps issue of supports_fp64 called with None. (#16136)
comfyanonymous Sep 6, 2026
e308cc7
Add Sparse Attention node (#16072)
kijai Sep 6, 2026
15eb748
chore: update embedded docs to v0.5.11 (#15947)
comfyui-wiki Sep 6, 2026
a99d1f9
Pause comfy compiler for long lived sparse allocations (#16148)
rattus128 Sep 6, 2026
82db403
Fix test_base_path_changes leaking a reloaded cli_args singleton (#16…
guill Sep 6, 2026
07dd46d
Fix the RGB/YUV conversion nodes on images with an alpha channel (#15…
christian-byrne Sep 6, 2026
7b3b262
Add color space conversion node. (#16135)
comfyanonymous Sep 6, 2026
d03a243
Fix Detect Edges (Canny) on images with an alpha channel (#15631)
christian-byrne Sep 6, 2026
25dfc16
Don't adjust the alpha channel in the image color adjustment nodes (#…
christian-byrne Sep 7, 2026
aa4582f
Fix Quantize Image on images with an alpha channel (#15630)
christian-byrne Sep 7, 2026
20f1a41
Fix Draw Text Overlay on images with an alpha channel (#15634)
christian-byrne Sep 7, 2026
f9c706f
Don't blend the alpha channel in the Blend Images node (#15625)
christian-byrne Sep 7, 2026
fbed745
Don't invert the alpha channel in the Invert Image node (#15622)
christian-byrne Sep 7, 2026
ea33b15
Fix transparent Porter-Duff blend modes (#15721)
tandede Sep 7, 2026
eb35786
Bump comfyui-frontend-package to 1.51.10 (#16118)
comfy-pr-bot Sep 7, 2026
313a76f
Disable int8 weight-only quantization on devices without torch._int_m…
chelsealong Sep 7, 2026
9ac7352
Fix registration issues (#15890)
guill Sep 7, 2026
41db8f4
Verify aotriton kernels actually launch before enabling pytorch atten…
0xDELUXA Sep 7, 2026
f5ed117
Remove useless code. (#16169)
comfyanonymous Sep 7, 2026
5bbdf8a
chore: Harmonize model attention nodes (#16154)
alexisrolland Sep 8, 2026
efa6c8f
Add LTXV generated-keyframe nodes and Freeze Latent (#16040)
adamoster Sep 8, 2026
00d34d9
Comfy Aimdo 0.5.3 + Memory compiler fixes (#16180)
rattus128 Sep 8, 2026
488e8f8
feat: Pixal3D multiview model support (CORE-421) (#16048)
kijai Sep 8, 2026
b7ebfd7
Fix quantized text encoder matmul gating and Gemma4 prefill cache pos…
kijai Sep 8, 2026
249c5a3
Cleaner way of enabling quantized mm on text gen but not on text enc.…
comfyanonymous Sep 8, 2026
0d0b6b5
Add LTXVAddLatentGuide for pinning a pre-encoded latent as a guide (#…
alexanderar Sep 8, 2026
421a1c2
Fix MiniMax H3 denoise masks (#15988)
poorpaper Sep 8, 2026
672ba9e
Only lock repo PRs after merging if they contain a CLA signature. (#1…
comfyanonymous Sep 9, 2026
be47aa2
[Partner Nodes] feat(OpenAI): add GPT Image 2.5 Flare and Sunburst mo…
bigcat88 Sep 9, 2026
02dfb63
chores: Update tooltips of 3D nodes (CORE-323) (#16179)
alexisrolland Sep 9, 2026
6517734
chore: update workflow templates to v0.11.57 (#16192)
comfyui-wiki Sep 9, 2026
3074d0e
Report the file saved by Save 3D (Advanced) as a standard 3d output i…
jtydhr88 Sep 9, 2026
40c4fcd
ComfyUI v0.35.0
comfyanonymous Sep 9, 2026
54e03f5
Add new model blueprints and reorganize subgraph categories (#14785)
comfyui-wiki Sep 9, 2026
6f3895e
main: bump the AMD Windows VA quota to 4TB (#16199)
rattus128 Sep 9, 2026
4989cdd
[Partner Noes] feat(OpenRouter): add Microsoft `mai-image-2.6` models…
bigcat88 Sep 9, 2026
be92396
quant_ops: drop the dead ROCm triton arch gate (#16211)
0xDELUXA Sep 9, 2026
7ea14e5
[Partner Nodes] feat(Gemini-LLM): Add Gemini 3.8 Flash to the Gemini …
bigcat88 Sep 10, 2026
a7b1d39
Update instructions for manual install on windows AMD. (#16217)
comfyanonymous Sep 10, 2026
6eba895
[Partner Nodes] feat(Tripo): migrate to the v3 API, add the Smart Seg…
bigcat88 Sep 10, 2026
5774ab9
[Partner Nodes] feat(OpenRouter): add auto aspect ratio to the MAI im…
bigcat88 Sep 10, 2026
1f641fd
chore: update workflow templates to v0.11.59 (#16233)
comfyui-wiki Sep 10, 2026
6338e4b
Fix h3 fun controlnet with comfy compiler. (#16240)
comfyanonymous Sep 10, 2026
1d48d9c
Add linear to ImageColorSpace. (#16247)
comfyanonymous Sep 11, 2026
d537de9
Implement Video Concatenate (CORE-436) (#16267)
rattus128 Sep 11, 2026
c40c94e
Fix unit tests (#16271)
alexisrolland Sep 11, 2026
1d91a82
feat: Marigold v2 support (CORE-431) (#16232)
kijai Sep 11, 2026
b058ec6
Support Yue2 music model. (#16250)
comfyanonymous Sep 11, 2026
7193f56
Bump comfyui-frontend-package to 1.52.7 (#16275)
christian-byrne Sep 12, 2026
c75d8c9
[Partner Nodes] feat(Bria): add new image edit nodes and the Video Er…
bigcat88 Sep 12, 2026
9113c08
[Partner Nodes] feat(client): consume estimated-duration headers for …
bigcat88 Sep 12, 2026
7dac1d2
Increase max song duration in Yue2 node. (#16292)
comfyanonymous Sep 12, 2026
7ba217d
Don't add noise to the alpha channel in the Add Noise to Image node (…
christian-byrne Sep 12, 2026
a20738f
Fix linear_input_act to respect _full_precision_mm fallback (#16285)
chelsealong Sep 12, 2026
98c7334
Fix yue2 AMD issues and add more controls to the generate ABC node. (…
comfyanonymous Sep 12, 2026
d43a5fa
Log typed asset scanner filesystem errors (#16096)
christian-byrne Sep 12, 2026
02d39c8
[Partner Nodes] feat(BFL): add the Flux Video Edit node (#16259)
bigcat88 Sep 13, 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.

27 changes: 27 additions & 0 deletions .ci/windows_amd_base_files/README_VERY_IMPORTANT.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
As of the time of writing this you need a recent driver. Updating to the latest driver is recommended.

HOW TO RUN:

If you have a AMD gpu:

run_amd_gpu.bat

If you have memory issues you can try enabling the new dynamic memory management by running comfyui with:

run_amd_gpu_enable_dynamic_vram.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