pythongosssss
e4b55560b4
fix value ranges
2026-02-16 11:38:59 -08:00
pythongosssss
6942d9d08a
update valid ranges
...
- threshold 0-100
- step 0+
2026-02-16 11:38:59 -08:00
Hunter Senft-Grupp
78d1798655
fix: move _initialized flag to end of GLContext.__init__
...
Prevents '_vao' attribute error when init fails partway through
and subsequent calls skip initialization due to early _initialized flag.
2026-02-16 11:38:59 -08:00
pythongosssss
9f4ef1a094
Add edge preserving blur
2026-02-16 11:38:59 -08:00
pythongosssss
0ff223bd33
print -> logger
2026-02-16 11:38:59 -08:00
pythongosssss
4cd2e02eee
rebuild blueprints
2026-02-16 11:38:59 -08:00
pythongosssss
38f38dbdb5
more fixes
2026-02-16 11:38:59 -08:00
pythongosssss
bb7a56b1f0
add multipass for faster blur
2026-02-16 11:38:59 -08:00
pythongosssss
5a78eb61cf
shader nit iteration
2026-02-16 11:38:59 -08:00
pythongosssss
b4afa4d52b
add glsl shader update system
2026-02-16 11:38:59 -08:00
pythongosssss
e249169852
hsb
2026-02-16 11:38:59 -08:00
pythongosssss
bd1f041ca1
brightness/contrast
2026-02-16 11:38:59 -08:00
pythongosssss
eff8d1a004
Add glow
2026-02-16 11:38:59 -08:00
pythongosssss
9e213f81ec
Add channels
2026-02-16 11:38:59 -08:00
pythongosssss
0f6a76442e
Add image operation blueprints
2026-02-16 11:38:59 -08:00
pythongosssss
c3d07bec6d
add diagnostics, update mac initialization
2026-01-30 12:26:04 -08:00
pythongosssss
59b955ff54
fix ci
...
perf: only read required outputs
2026-01-29 20:14:26 -08:00
pythongosssss
1263d6fe88
add additional support for egl & osmesa backends
2026-01-29 20:07:40 -08:00
pythongosssss
23572c6314
tidy
2026-01-28 20:59:01 -08:00
pythongosssss
d809ef8fb1
remove cpu support
2026-01-28 20:58:04 -08:00
pythongosssss
a4317314d2
convert to using PyOpenGL and glfw
2026-01-28 20:48:20 -08:00
pythongosssss
aaea976f36
fix line endings
2026-01-28 11:02:17 -08:00
pythongosssss
cee092213e
Merge remote-tracking branch 'origin/master' into pysssss/basic-glsl-shader-node
2026-01-28 10:50:12 -08:00
pythongosssss
3da0e9c367
fix casing
2026-01-28 10:47:36 -08:00
pythongosssss
9fa8202620
Try fix build
2026-01-28 10:47:36 -08:00
pythongosssss
b4438c9baf
Support multiple outputs
2026-01-28 10:47:36 -08:00
ComfyUI Wiki
1711020904
chore: update workflow templates to v0.8.27 ( #12141 )
2026-01-28 12:48:02 -05:00
Dr.Lt.Data
d9b8567547
bump manager version to 4.1b1 ( #12140 )
2026-01-28 12:47:37 -05:00
Alexander Piskun
6c5f906bf2
feat(api-nodes): add Grok Imagine nodes ( #12136 )
2026-01-28 12:46:57 -05:00
comfyanonymous
4f5bd39b1c
Update Python 3.14 compatibility notes in README ( #12127 )
2026-01-27 19:58:48 -05:00
guill
dcff27fe3f
Add support for dev-only nodes. ( #12106 )
...
When a node is declared as dev-only, it doesn't show in the default UI
unless the dev mode is enabled in the settings. The intention is to
allow nodes related to unit testing to be included in ComfyUI
distributions without confusing the average user.
2026-01-27 13:03:29 -08:00
comfyanonymous
09725967cf
ComfyUI version v0.11.0
2026-01-26 23:08:01 -05:00
ComfyUI Wiki
5f62440fbb
chore: update workflow templates to v0.8.24 ( #12103 )
2026-01-26 22:47:33 -05:00
ComfyUI Wiki
ac91c340f4
Update workflow templates to v0.8.23 ( #12102 )
2026-01-26 21:39:39 -05:00
comfyanonymous
2db3b0ff90
Update amd portable for rocm 7.2 ( #12101 )
...
* Update amd portable for rocm 7.2
* Update Python patch version in release workflow
2026-01-26 19:49:31 -05:00
rattus
6516ab335d
wan-vae: Switch off feature cache for single frame ( #12090 )
...
The code throughout is None safe to just skip the feature cache saving
step if none. Set it none in single frame use so qwen doesn't burn VRAM
on the unused cache.
2026-01-26 19:40:19 -05:00
Jukka Seppänen
ad53e78f11
Fix Noise_EmptyNoise when using nested latents ( #12089 )
2026-01-26 19:25:00 -05:00
Alexander Piskun
29011ba87e
[API Nodes] add Magnific nodes ( #11986 )
...
* feat(api-nodes): add Magnific nodes
* aggressive downscaling should not be performed
* disable upscaler nodes
---------
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-01-26 14:10:09 -08:00
Alexander Piskun
cd4985e2f3
chore(api-nodes): remove ByteDanceImageEditNode node (seededit) ( #12069 )
...
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-01-26 13:58:33 -08:00
Tavi Halperin
bfe31d0b9d
IC-LoRA: support small grid ( #12074 )
2026-01-26 15:33:19 -05:00
comfyanonymous
2129e7d278
Fix mistral 3 tokenizer code failing on latest transformers version and other breakage. ( #12095 )
...
* Fix mistral 3 tokenizer code failing on latest transformers version.
* Add requests to the requirements
2026-01-26 11:39:00 -05:00
comfyanonymous
7ee77ff038
Add name to LoraLoaderModelOnly. ( #12078 )
2026-01-25 21:01:55 -05:00
comfyanonymous
26c5bbb875
Move nodes from previous PR into their own file. ( #12066 )
2026-01-24 23:02:32 -05:00
Kohaku-Blueleaf
a97c98068f
[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system ( #11958 )
...
* Add API of bypass forward module
* bypass implementation
* add bypass fwd into nodes list/trainer
2026-01-24 22:56:22 -05:00
comfyanonymous
635406e283
Only enable fp16 on z image models that actually support it. ( #12065 )
2026-01-24 22:32:28 -05:00
pythongosssss
ed6002cb60
add support for kwargs inputs to allow arbitrary inputs from frontend ( #12063 )
...
used to output selected combo index
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-01-24 17:30:40 -08:00
Alexander Piskun
bc72d7f8d1
[API Nodes] add TencentHunyuan3D nodes ( #12026 )
...
* feat(api-nodes): add TencentHunyuan3D nodes
* add "(Pro)" to display name
---------
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2026-01-24 17:10:09 -08:00
comfyanonymous
aef4e13588
Make empty latent node work with other models. ( #12062 )
2026-01-24 19:23:20 -05:00
rattus
4e6a1b66a9
speed up and reduce VRAM of QWEN VAE and WAN (less so) ( #12036 )
...
* ops: introduce autopad for conv3d
This works around pytorch missing ability to causal pad as part of the
kernel and avoids massive weight duplications for padding.
* wan-vae: rework causal padding
This currently uses F.pad which takes a full deep copy and is liable to
be the VRAM peak. Instead, kick spatial padding back to the op and
consolidate the temporal padding with the cat for the cache.
* wan-vae: implement zero pad fast path
The WAN VAE is also QWEN where it is used single-image. These
convolutions are however zero padded 3d convolutions, which means the
VAE is actually just 2D down the last element of the conv weight in
the temporal dimension. Fast path this, to avoid adding zeros that
then just evaporate in convoluton math but cost computation.
2026-01-23 19:56:14 -05:00
comfyanonymous
9cf299a9f9
Make regular empty latent node work properly on flux 2 variants. ( #12050 )
2026-01-23 19:50:48 -05:00
