Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3639 commits
Select commit Hold shift + click to select a range
f719a9d
Adjust memory usage factor of zeta model. (#12746)
comfyanonymous Mar 3, 2026
b6ddc59
CURVE type (#12581)
jtydhr88 Mar 4, 2026
ac6513e
DynamicVram: Add casting / fix torch Buffer weights (#12749)
rattus128 Mar 4, 2026
eb01173
Fix VideoFromComponents.save_to crash when writing to BytesIO (#12683)
artokun Mar 4, 2026
d531e3f
model_patcher: Improve dynamic offload heuristic (#12759)
rattus128 Mar 4, 2026
9b85cf9
Comfy Aimdo 0.2.5 + Fix offload performance in DynamicVram (#12754)
rattus128 Mar 4, 2026
0a7446a
Pass tokens when loading text gen model for text generation (#12755)
kijai Mar 4, 2026
8811db5
comfy-aimdo 0.2.6 (#12764)
rattus128 Mar 4, 2026
ac4a943
Initial load device should be cpu when using dynamic vram. (#12766)
comfyanonymous Mar 4, 2026
43c64b6
Support the LTXAV 2.3 model. (#12773)
comfyanonymous Mar 5, 2026
f2ee7f2
Fix cublas ops on dynamic vram. (#12776)
comfyanonymous Mar 5, 2026
c5fe8ac
chore: update workflow templates to v0.9.6 (#12778)
comfyui-wiki Mar 5, 2026
4941671
Fix cuda getting initialized in cpu mode. (#12779)
comfyanonymous Mar 5, 2026
c842854
chore: update workflow templates to v0.9.7 (#12780)
comfyui-wiki Mar 5, 2026
e04d0db
ComfyUI v0.16.0
comfyanonymous Mar 5, 2026
bd21363
feat(api-nodes-xAI): updated models, pricing, added features (#12756)
bigcat88 Mar 5, 2026
9cdfd74
feat(api-nodes): enable Kling 3.0 Motion Control (#12785)
bigcat88 Mar 5, 2026
da29b79
Update workflow templates to v0.9.8 (#12788)
comfyui-wiki Mar 5, 2026
6ef82a8
ComfyUI v0.16.1
comfyanonymous Mar 5, 2026
6481569
comfy-aimdo 0.2.7 (#12791)
rattus128 Mar 5, 2026
42e0e02
ops: Handle CPU weight in VBAR caster (#12792)
rattus128 Mar 5, 2026
5073da5
chore: update workflow templates to v0.9.10 (#12793)
comfyui-wiki Mar 5, 2026
1c3b651
Refactor. (#12794)
comfyanonymous Mar 5, 2026
50549aa
ComfyUI v0.16.2
comfyanonymous Mar 5, 2026
8befce5
Add manual cast to LTX2 vocoder conv_transpose1d (#12795)
kijai Mar 5, 2026
17b43c2
LTX audio vae novram fixes. (#12796)
comfyanonymous Mar 5, 2026
58017e8
feat: add causal_fix parameter to add_keyframe_index and append_keyfr…
tavihalperin Mar 5, 2026
1c21828
ComfyUI v0.16.3
comfyanonymous Mar 5, 2026
e544c65
feat: add Math Expression node with simpleeval evaluation (#12687)
dante01yoon Mar 6, 2026
3b93d5d
feat(api-nodes): add TencentSmartTopology node (#12741)
bigcat88 Mar 6, 2026
34e55f0
feat(api-nodes): add Gemini 3.1 Flash Lite model to LLM node (#12803)
bigcat88 Mar 6, 2026
f466b06
Fix fp16 audio encoder models (#12811)
rattus128 Mar 6, 2026
d69d308
Don't run TE on cpu when dynamic vram enabled. (#12815)
comfyanonymous Mar 7, 2026
afc00f0
Fix requirements version. (#12817)
comfyanonymous Mar 7, 2026
6ac8152
chore: update workflow templates to v0.9.11 (#12821)
comfyui-wiki Mar 7, 2026
bcf1a1f
mm: reset_cast_buffers: sync compute stream before free (#12822)
rattus128 Mar 7, 2026
a7a6335
ComfyUI v0.16.4
comfyanonymous Mar 7, 2026
29b24cb
refactor(assets): modular architecture + async two-phase scanner & ba…
luke-mino-altherr Mar 8, 2026
7723f20
comfy-aimdo 0.2.9 (#12840)
rattus128 Mar 8, 2026
e4b0bb8
Import assets seeder later, print some package versions. (#12841)
comfyanonymous Mar 8, 2026
06f85e2
Fix text encoder lora loading for wrapped models (#12852)
kijai Mar 9, 2026
814dab9
Update workflow templates to v0.9.18 (#12857)
comfyui-wiki Mar 10, 2026
740d998
fix(manager): improve install guidance when comfyui-manager is not in…
ltdrdata Mar 10, 2026
c4fb027
Add a way for nodes to add pre attn patches to flux model. (#12861)
comfyanonymous Mar 10, 2026
a912809
model_detection: deep clone pre edited edited weights (#12862)
rattus128 Mar 10, 2026
535c16c
Widen OOM_EXCEPTION to AcceleratorError form (#12835)
rattus128 Mar 10, 2026
8086468
main: switch on faulthandler (#12868)
rattus128 Mar 10, 2026
3ad36d6
Allow model patches to have a cleanup function. (#12878)
comfyanonymous Mar 11, 2026
9642e44
Add pre attention and post input patches to qwen image model. (#12879)
comfyanonymous Mar 11, 2026
980621d
comfy-aimdo 0.2.10 (#12890)
rattus128 Mar 11, 2026
3365008
feat(api-nodes): add Reve Image nodes (#12848)
bigcat88 Mar 11, 2026
4f4f865
fix: guard torch.AcceleratorError for compatibility with torch < 2.8.…
adiborochov Mar 11, 2026
f6274c0
Fix issue with batch_size > 1 on some models. (#12892)
comfyanonymous Mar 11, 2026
abc87d3
Bump comfyui-frontend-package to 1.41.15 (#12891)
comfy-pr-bot Mar 11, 2026
9ce4c3d
Bump comfyui-frontend-package to 1.41.16 (#12894)
comfy-pr-bot Mar 12, 2026
8f9ea49
Bump comfy-kitchen version to 0.2.8 (#12895)
comfyanonymous Mar 12, 2026
44f1246
Support flux 2 klein kv cache model: Use the FluxKVCache node. (#12905)
comfyanonymous Mar 12, 2026
73d9599
add painter node (#12294)
jtydhr88 Mar 12, 2026
3fa8c56
fix: use frontend-compatible format for Float gradient_stops (#12789)
jtydhr88 Mar 12, 2026
712411d
chore: update workflow templates to v0.9.21 (#12908)
comfyui-wiki Mar 12, 2026
47e1e31
Lower kv cache memory usage. (#12909)
comfyanonymous Mar 12, 2026
8d9faaa
Update requirements.txt (#12910)
christian-byrne Mar 12, 2026
af7b4a9
feat: Add CacheProvider API for external distributed caching (#12056)
deepme987 Mar 12, 2026
d1d53c1
Revert "feat: Add CacheProvider API for external distributed caching …
comfyanonymous Mar 13, 2026
5df1427
Fix audio extraction and truncation bugs (#12652)
PxTicks Mar 13, 2026
63d1bbd
ComfyUI v0.17.0
comfyanonymous Mar 13, 2026
4a8cf35
Revert "Revert "feat: Add CacheProvider API for external distributed …
deepme987 Mar 13, 2026
f9ceed9
fix(api-nodes): Tencent TextToModel and ImageToModel nodes (#12680)
bigcat88 Mar 13, 2026
6cd35a0
Bump comfyui-frontend-package to 1.41.19 (#12923)
comfy-pr-bot Mar 13, 2026
e1f10ca
bump manager version to 4.1b4 (#12930)
ltdrdata Mar 14, 2026
7810f49
comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windo…
rattus128 Mar 14, 2026
16cd8d8
Update README. (#12931)
comfyanonymous Mar 14, 2026
4c4be1b
comfy-aimdo 0.2.12 (#12941)
rattus128 Mar 14, 2026
e0982a7
fix: use no-store cache headers to prevent stale frontend chunks (#12…
christian-byrne Mar 14, 2026
1c5db73
feat: Support mxfp8 (#12907)
kijai Mar 14, 2026
c711b8f
Add --fp16-intermediates to use fp16 for intermediate values between …
comfyanonymous Mar 14, 2026
4941cd0
Update comfyui-frontend-package to version 1.41.20 (#12954)
comfyanonymous Mar 14, 2026
0904cc3
LTXV: Accumulate VAE decode results on intermediate_device (#12955)
kijai Mar 15, 2026
192cb8e
bump manager version to 4.1b5 (#12957)
ltdrdata Mar 15, 2026
e84a200
ops: opt out of deferred weight init if subclassed (#12967)
rattus128 Mar 15, 2026
d062bec
Make EmptyLatentImage follow intermediate dtype. (#12974)
comfyanonymous Mar 15, 2026
3814bf4
Enable Pytorch Attention for gfx1150 (#12973)
lostdisc Mar 15, 2026
593be20
feat: add essentials_category to nodes and blueprints for Essentials …
christian-byrne Mar 15, 2026
2bd4d82
feat(assets): align local API with cloud spec (#12863)
luke-mino-altherr Mar 16, 2026
7d5f525
ci: add check to block AI agent Co-authored-by trailers in PRs (#12799)
christian-byrne Mar 16, 2026
b202f84
Skip running model finalizers at exit (#12994)
blepping Mar 16, 2026
7a16e8a
Add --enable-dynamic-vram options to force enable it. (#13002)
comfyanonymous Mar 16, 2026
20561aa
[Trainer] FP4, 8, 16 training by native dtype support and quant linea…
KohakuBlueleaf Mar 17, 2026
ca17fc8
Fix potential issue. (#13009)
comfyanonymous Mar 17, 2026
9a870b5
fix: atomic writes for userdata to prevent data loss on crash (#12987)
christian-byrne Mar 17, 2026
8cc746a
fix: disable SageAttention for Hunyuan3D v2.1 DiT (#12772)
paulomuggler Mar 17, 2026
379fbd1
chore: update workflow templates to v0.9.26 (#13012)
comfyui-wiki Mar 17, 2026
ed7c2c6
Mark weight_dtype as advanced input in Load Diffusion Model node (#12…
christian-byrne Mar 17, 2026
1a157e1
Reduce LTX VAE VRAM usage and save use cases from OOMs/Tiler (#13013)
rattus128 Mar 17, 2026
035414e
Reduce WAN VAE VRAM, Save use cases for OOM/Tiler (#13014)
rattus128 Mar 17, 2026
8b9d039
bump manager version to 4.1b6 (#13022)
ltdrdata Mar 17, 2026
735a046
Inplace VAE output processing to reduce peak RAM consumption. (#13028)
kijai Mar 18, 2026
68d542c
Fix case where pixel space VAE could cause issues. (#13030)
comfyanonymous Mar 18, 2026
cad24ce
cascade: remove dead weight init code (#13026)
rattus128 Mar 18, 2026
b941913
fix: run text encoders on MPS GPU instead of CPU for Apple Silicon (#…
k06a Mar 18, 2026
0695702
fix(api-nodes): add support for "thought_image" in Nano Banana 2 and …
bigcat88 Mar 18, 2026
b67ed2a
Update comfyui-frontend-package version to 1.41.21 (#13035)
DrJKL Mar 18, 2026
dcd6595
Make more intermediate values follow the intermediate dtype. (#13051)
comfyanonymous Mar 18, 2026
9fff091
Further Reduce LTX VAE decode peak RAM usage (#13052)
kijai Mar 18, 2026
56ff88f
Fix regression. (#13053)
comfyanonymous Mar 18, 2026
f6b869d
fp16 intermediates doen't work for some text enc models. (#13056)
comfyanonymous Mar 18, 2026
fabed69
ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reduc…
rattus128 Mar 19, 2026
6589562
ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reduc…
rattus128 Mar 19, 2026
ab14541
memory: Add more exclusion criteria to pinned read (#13067)
rattus128 Mar 19, 2026
fd0261d
Reduce tiled decode peak memory (#13050)
kijai Mar 19, 2026
8458ae2
Revert "fix: run text encoders on MPS GPU instead of CPU for Apple Si…
comfyanonymous Mar 19, 2026
82b868a
Fix VRAM leak in tiler fallback in video VAEs (#13073)
rattus128 Mar 20, 2026
f49856a
ltx: vae: Fix missing init variable (#13074)
rattus128 Mar 20, 2026
e4455fd
[API Nodes] mark seedream-3-0-t2i and seedance-1-0-lite models as dep…
bigcat88 Mar 20, 2026
589228e
Add slice_cond and per-model context window cond resizing (#12645)
drozbay Mar 20, 2026
c646d21
feat(api-nodes): add Quiver SVG nodes (#13047)
bigcat88 Mar 20, 2026
45d5c83
Make EmptyImage node follow intermediate device/dtype. (#13079)
comfyanonymous Mar 20, 2026
87cda1f
Move inline comfy.context_windows imports to top-level in model_base.…
Kosinkadink Mar 21, 2026
dc719cd
ComfyUI version 0.18.0
comfyanonymous Mar 21, 2026
a11f68d
Fix canny node not working with fp16. (#13085)
comfyanonymous Mar 21, 2026
b5d32e6
Fix sampling issue with fp16 intermediates. (#13099)
comfyanonymous Mar 21, 2026
11c15d8
Fix fp16 intermediates giving different results. (#13100)
comfyanonymous Mar 21, 2026
25b6d1d
wan: vae: Fix light/color change (#13101)
rattus128 Mar 21, 2026
ebf6b52
ComfyUI v0.18.1
comfyanonymous Mar 22, 2026
d49420b
LongCat-Image edit (#13003)
Talmaj Mar 22, 2026
6265a23
Add warning for users who disable dynamic vram. (#13113)
comfyanonymous Mar 22, 2026
da6edb5
bump manager version to 4.1b8 (#13108)
ltdrdata Mar 23, 2026
e87858e
feat: LTX2: Support reference audio (ID-LoRA) (#13111)
kijai Mar 23, 2026
2d4970f
Update frontend version to 1.42.8 (#13126)
comfyanonymous Mar 24, 2026
2d5fd3f
fix: set default values of Color Adjustment node to zero (#13084)
kaili-yang Mar 24, 2026
f9ec85f
feat(api-nodes): update xAI Grok nodes (#13140)
bigcat88 Mar 24, 2026
c2862b2
Update templates package version. (#13141)
comfyanonymous Mar 24, 2026
8e73678
CURVE node (#12757)
jtydhr88 Mar 24, 2026
a0a64c6
Add Number Convert node (#13041)
dante01yoon Mar 24, 2026
5ebb0c2
FP8 bwd training (#13121)
KohakuBlueleaf Mar 25, 2026
7d5534d
feat(assets): register output files as assets after prompt execution …
luke-mino-altherr Mar 25, 2026
b53b10e
Fix Train LoRA crash when training_dtype is "none" with bfloat16 LoRA…
Krishnachaitanyakc Mar 25, 2026
a55835f
fix(api-nodes): made Reve node price badges more precise (#13154)
bigcat88 Mar 25, 2026
3b15651
bump manager version to 4.1 (#13156)
ltdrdata Mar 25, 2026
6580a6b
fix(number-convert): preserve int precision for large numbers (#13147)
dante01yoon Mar 25, 2026
404d7b9
feat: Support Qwen3.5 text generation models (#12771)
kijai Mar 26, 2026
3eba2dc
fix(assets): recognize temp directory in asset category resolution (#…
luke-mino-altherr Mar 26, 2026
2a1f402
Make Qwen 8B work with TextGenerate node. (#13160)
comfyanonymous Mar 26, 2026
b0fd65e
fix: regression in text generate with LTXAV model (#13170)
kijai Mar 26, 2026
8165485
feat(api-nodes): added new Topaz model (#13175)
bigcat88 Mar 26, 2026
359559c
chore: update workflow templates to v0.9.38 (#13176)
comfyui-wiki Mar 26, 2026
1dc64f3
feat: add curve inputs and raise uniform limit for GLSL shader node (…
jtydhr88 Mar 27, 2026
b1fdbeb
Fix blur and sharpen nodes not working with fp16 intermediates. (#13181)
comfyanonymous Mar 27, 2026
225c52f
fix: register image/svg+xml MIME type for .svg files (#13186)
viva-jinyi Mar 27, 2026
85b7495
chore: update workflow templates to v0.9.39 (#13196)
comfyui-wiki Mar 27, 2026
6a2cdb8
fix(api-nodes-nanobana): raise error when not output image is present…
bigcat88 Mar 27, 2026
3a56201
Allow flux conditioning without a pooled output. (#13198)
comfyanonymous Mar 28, 2026
3696c5b
Add `has_intermediate_output` flag for nodes with interactive UI (#13…
jtydhr88 Mar 28, 2026
b353a7c
Integrate RAM cache with model RAM management (#13173)
rattus128 Mar 28, 2026
fc1fdf3
fix: avoid nested sampler function calls in Color Curves shader (#13209)
jtydhr88 Mar 28, 2026
3f77450
Fix #13214 (#13216)
comfyanonymous Mar 29, 2026
a500f1e
CORE-13 feat: Support RT-DETRv4 detection model (#12748)
kijai Mar 29, 2026
d113d1c
feat(api-nodes-Tencent3D): allow smaller possible face_count; add uv_…
bigcat88 Mar 29, 2026
8d723d2
Fix/tweak pinned memory accounting (#13221)
rattus128 Mar 29, 2026
537c10d
Update README.md with latest AMD Linux pytorch. (#13228)
comfyanonymous Mar 30, 2026
55e6478
Rename utils/string nodes with Text prefix and add search aliases (#1…
christian-byrne Mar 30, 2026
076639f
Update README with note on model support (#13235)
comfyanonymous Mar 31, 2026
e2ddf28
Fix some fp8 scaled checkpoints no longer working. (#13239)
comfyanonymous Mar 31, 2026
7d43768
chore: update workflow templates to v0.9.41 (#13242)
comfyui-wiki Apr 1, 2026
0c63b4f
Remove dead code. (#13251)
comfyanonymous Apr 2, 2026
76b75f3
Fix some issue with insecure browsers. (#13261)
comfyanonymous Apr 2, 2026
5de94e7
feat(api-nodes): new Partner nodes for Wan2.7 (#13264)
bigcat88 Apr 3, 2026
eb0686b
Update template to 0.9.43 (#13265)
comfyui-wiki Apr 3, 2026
f21f6b2
Add portable release for intel XPU. (#13272)
comfyanonymous Apr 3, 2026
13917b3
Nightly Nvidia pytorch is now cu132 (#13288)
comfyanonymous Apr 4, 2026
8cbbea8
chore: update workflow templates to v0.9.44 (#13290)
comfyui-wiki Apr 5, 2026
4b1444f
Update README.md with new frontend release cycle. (#13301)
comfyanonymous Apr 5, 2026
7083484
image histogram node (#13153)
jtydhr88 Apr 6, 2026
61c2387
Ace step empty latent nodes follow intermediate dtype. (#13313)
comfyanonymous Apr 7, 2026
50076f3
format blueprint (#13315)
jtydhr88 Apr 7, 2026
40862c0
Support Ace Step 1.5 XL model. (#13317)
comfyanonymous Apr 7, 2026
b615af1
Add support for small flux.2 decoder (#13314)
huemin-art Apr 7, 2026
2d861fb
Basic intel standalone package .bat (#13333)
comfyanonymous Apr 9, 2026
3d4aca8
Bump comfyui-frontend-package version to 1.42.10 (#13346)
comfyanonymous Apr 10, 2026
e6be419
should use 0 as defalut for brightness (#13345)
jtydhr88 Apr 10, 2026
5410ed3
fix(api-nodes): fix GrokVideoReferenceNode price badge (#13354)
bigcat88 Apr 10, 2026
b920bdd
chore: update workflow templates to v0.9.45 (#13353)
comfyui-wiki Apr 10, 2026
a134423
SDPose: resize input always (#13349)
kijai Apr 10, 2026
a2840e7
Make ImageUpscaleWithModel node work with intermediate device and dty…
comfyanonymous Apr 11, 2026
55ebd28
Add a supports_fp64 function. (#13368)
comfyanonymous Apr 12, 2026
31283d2
Implement Ernie Image model. (#13369)
comfyanonymous Apr 12, 2026
9719323
Update quant doc so it's not completely wrong. (#13381)
comfyanonymous Apr 13, 2026
c2657d5
Fix typo. (#13382)
comfyanonymous Apr 13, 2026
ee2db74
feat(api-nodes): add SeeDance 2.0 nodes (#13364)
bigcat88 Apr 13, 2026
559501e
chore: update workflow templates to v0.9.47 (#13385)
comfyui-wiki Apr 13, 2026
acd7185
ComfyUI v0.19.0
comfyanonymous Apr 13, 2026
402ff1c
Fix issue with ernie image. (#13393)
comfyanonymous Apr 13, 2026
722bc73
Make text generation work with ministral model. (#13395)
comfyanonymous Apr 14, 2026
35dfcbb
[Partner Nodes] add Sonilo Audio nodes (#13391)
bigcat88 Apr 14, 2026
fed4ac0
chore: update workflow templates to v0.9.50 (#13399)
comfyui-wiki Apr 14, 2026
c16db7f
Bump comfyui-frontend-package to 1.42.11 (#13398)
comfy-pr-bot Apr 14, 2026
c5569e8
Add string output to preview text node. (#13406)
comfyanonymous Apr 14, 2026
7ce3f64
Update workflow templates to v0.9.54 (#13412)
comfyui-wiki Apr 15, 2026
cb0bbde
Fix ernie on devices that don't support fp64. (#13414)
comfyanonymous Apr 15, 2026
8f37471
ComfyUI v0.19.1
comfyanonymous Apr 15, 2026
1de83f9
Fix OOM regression in _apply() for quantized models during inference …
jkyamog Apr 15, 2026
e9a2d1e
Add a way to disable default template in text gen node. (#13424)
comfyanonymous Apr 16, 2026
b41ab53
Use `ErnieTEModel_` not `ErnieTEModel`. (#13431)
bedovyy Apr 16, 2026
d0c53c5
feat(api-nodes): add 1080p resolution for SeeDance 2.0 model (#13437)
bigcat88 Apr 17, 2026
1391579
Add JsonExtractString node. (#13435)
comfyanonymous Apr 17, 2026
c033bbf
ComfyUI v0.19.2
comfyanonymous Apr 17, 2026
05f7531
nodes_textgen: Implement use_default_template for LTX (#13451)
rattus128 Apr 17, 2026
541fd10
fix(api-nodes): corrected StabilityAI price badges (#13454)
bigcat88 Apr 17, 2026
4f48be4
feat(api-nodes): add new "arrow-1.1" and "arrow-1.1-max" SVG models (…
bigcat88 Apr 17, 2026
f8d92cf
chore: update workflow templates to v0.9.57 (#13455)
comfyui-wiki Apr 17, 2026
9635c2e
fix(api-nodes): make "obj" output optional in Hunyuan3D Text and Imag…
bigcat88 Apr 17, 2026
3086026
ComfyUI v0.19.3
comfyanonymous Apr 17, 2026
b9dedea
feat: SUPIR model support (CORE-17) (#13250)
kijai Apr 19, 2026
3d816db
Some optimizations to make Ernie inference a bit faster. (#13472)
comfyanonymous Apr 19, 2026
138571d
fix: append directory type annotation to internal files endpoint resp…
Abdulrehman-PIAIC80387 Apr 19, 2026
fc5f4a9
Add link to Intel portable to Readme. (#13477)
comfyanonymous Apr 20, 2026
543e9fb
fix: pin SQLAlchemy>=2.0 in requirements.txt (fixes #13036) (#13316)
octo-patch Apr 20, 2026
c514890
Refactor io to IO in nodes_ace.py (#13485)
comfyanonymous Apr 21, 2026
e75f775
Bump comfyui-frontend-package to 1.42.12 (#13489)
comfy-pr-bot Apr 21, 2026
ad94d47
Make the ltx audio vae more native. (#13486)
comfyanonymous Apr 21, 2026
b38dd0f
feat(api-nodes): add automatic downscaling of videos for ByteDance 2 …
bigcat88 Apr 21, 2026
eb22225
Support standalone LTXV audio VAEs (#13499)
kijai Apr 21, 2026
1e1d4f1
[Partner Nodes] added 4K resolution for Veo models; added Veo 3 Lite…
bigcat88 Apr 21, 2026
102773c
Bump comfyui-frontend-package to 1.42.14 (#13493)
comfy-pr-bot Apr 21, 2026
43a1263
Add gpt-image-2 as version option (#13501)
AustinMroz Apr 22, 2026
529c802
Allow logging in comfy app files. (#13505)
comfyanonymous Apr 22, 2026
6045c11
chore: update workflow templates to v0.9.59 (#13507)
comfyui-wiki Apr 22, 2026
91e1f45
fix(veo): reject 4K resolution for veo-3.0 models in Veo3VideoGenerat…
MillerMedia Apr 22, 2026
db85cf0
feat: RIFE and FILM frame interpolation model support (CORE-29) (#13258)
kijai Apr 22, 2026
cc6f950
fix: use Parameter assignment for Stable_Zero123 cc_projection weight…
octo-patch Apr 22, 2026
9949c19
Derive InterruptProcessingException from BaseException (#13523)
blepping Apr 22, 2026
cb388e2
bump manager version to 4.2.1 (#13516)
ltdrdata Apr 22, 2026
ec4b165
ModelPatcherDynamic: force cast stray weights on comfy layers (#13487)
rattus128 Apr 22, 2026
0be87b0
Update logging level for invalid version format (#13526)
comfyanonymous Apr 23, 2026
e988df7
[Partner Nodes] add SD2 real human support (#13509)
bigcat88 Apr 23, 2026
749d5b4
feat: SAM (segment anything) 3.1 support (CORE-34) (#13408)
kijai Apr 23, 2026
3cdc0d5
[Partner Nodes] GPTImage: fix price badges, add new resolutions (#13519)
bigcat88 Apr 23, 2026
5edbdf4
chore: update workflow templates to v0.9.61 (#13533)
comfyui-wiki Apr 23, 2026
2a14e1e
chore: update embedded docs to v0.4.4 (#13535)
comfyui-wiki Apr 23, 2026
abf3d56
add 4K resolution to Kling nodes (#13536)
bigcat88 Apr 23, 2026
6fbb6b6
Fix LTXV Reference Audio node (#13531)
kijai Apr 23, 2026
ef8f3cb
comfy-aimdo 0.2.14: Hotfix async allocator estimations (#13534)
rattus128 Apr 23, 2026
084e08c
Disable sageattention for SAM3 (#13529)
kijai Apr 23, 2026
2327fa1
execution: Add anti-cycle validation (#13169)
rattus128 Apr 23, 2026
47cceca
chore: update workflow templates to v0.9.62 (#13539)
comfyui-wiki Apr 23, 2026
c5d9eda
Print more tensor values in the preview any node. (#13544)
comfyanonymous Apr 24, 2026
00d2f40
fix: use textureSize instead of u_resolution for texel size in blur/s…
jtydhr88 Apr 24, 2026
2e05037
range type (#13322)
jtydhr88 Apr 24, 2026
443074e
Add OpenAPI 3.1 specification for ComfyUI API (#13397)
MillerMedia Apr 24, 2026
7636599
chore(api-nodes): add upcoming-deprecation notice to Sora nodes (#13549)
bigcat88 Apr 24, 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 --disable-smart-memory
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