netjerikh
0d2334de6d
Added multithread option to ColorMatch node
2025-07-18 11:54:19 +03:00
kijai
ad37ce656c
Make multi-input node inputs optional
2025-07-16 16:54:06 +03:00
kijai
ab8cac5396
Add LoraExtractKJ
...
Improved Lora extraction node
- build in diff substraction
- lowrank algo for quick extraction
- dtype selection
2025-07-16 14:02:31 +03:00
kijai
730edb08c1
Change JoinStrings inputs to optional
2025-07-16 11:12:21 +03:00
kijai
fca4aa2a15
ImageResizeKJv2: output padded area as mask if no input mask to resize
2025-07-15 14:57:57 +03:00
kijai
d9425173e7
Add ImageBatchJoinWithTransition
2025-07-14 16:40:23 +03:00
kijai
f20cb4c108
Update image_nodes.py
2025-07-14 15:27:53 +03:00
kijai
4549812bcc
Update CrossFadeImages to allow joining different batch sizes
2025-07-14 15:24:05 +03:00
kijai
22e722bafe
Update image_nodes.py
2025-07-10 18:59:17 +03:00
kijai
cabfcb2245
ImageResizeKJv2: Allow changing pad direction, add output info display
2025-07-10 18:56:25 +03:00
kijai
479cde218b
Update nodes.py
2025-07-08 13:56:58 +03:00
kijai
5c19bd835a
typo
2025-07-06 23:57:29 +03:00
kijai
6a0c755c56
these should not be output nodes...
2025-07-06 23:06:20 +03:00
kijai
ee0eb6696b
Use node_typing for ANY -inputs
2025-07-04 13:04:18 +03:00
kijai
40d9d84b68
Update mask_nodes.py
2025-07-03 20:45:10 +03:00
kijai
1f653a8d96
ReplaceImagesInBatch: Allow replacing only masks without images
2025-07-03 17:51:40 +03:00
kijai
ff49e1b01f
Add sageattn++ as selectable mode for easier testing
2025-07-01 12:26:27 +03:00
kijai
6363376a17
Add optional mask resiszing to ImageResizeKJv2, allow lanczos for mask resizing
2025-07-01 12:22:37 +03:00
kijai
fbc779a7bd
Allow negative values in INTConstant
2025-06-30 12:03:50 +03:00
kijai
f7eb33abc8
I remembered
...
Should keep the id or node title methods viable, though not recommended
2025-06-18 11:03:51 +03:00
kijai
24f10ca90c
Don't run WidgetToString on each queue...
...
I can't remember the reason for this, if it ever was necessary, it doesn't seem to be anymore...
2025-06-18 10:42:57 +03:00
kijai
ff98412479
Check if folder contents change on LoadImagesFromFolderKJ
2025-06-16 17:31:35 +03:00
kijai
7afb0f906a
Update model_optimization_nodes.py
2025-06-16 00:35:53 +03:00
kijai
d584c711a3
Experimental NAG node
2025-06-15 22:05:24 +03:00
kijai
ed8294d7fb
Add new "speed" sampling mode to SplineEditor
2025-06-09 18:16:58 +03:00
kijai
1fbf4805f1
SplineEditor updates
2025-06-09 17:59:31 +03:00
kijai
dfe7a909a4
Update model_optimization_nodes.py
2025-06-09 04:30:00 +03:00
kijai
e96a028254
Support VACE with TeaCache
2025-06-09 02:58:41 +03:00
kijai
5736669288
Support multiple splines on CreateShapeImageOnPath
2025-06-08 20:40:14 +03:00
kijai
87b8f85103
Fix Wan enhance a video disabling sageattention patch
2025-06-06 15:46:33 +03:00
kijai
f35bb4d336
Don't return coordinates as list if only one spline
2025-06-04 21:57:21 +03:00
kijai
9682804efb
remove print
2025-06-04 10:15:19 +03:00
kijai
76d67a963e
Remove redundant SD3 API Node
2025-06-03 20:45:28 +03:00
kijai
ea5482a6ee
Initial mostly working multiple splines for SplineEditor
...
Probably buggy and clumsy to use, but workable and way better than having to use multiple SplineEditors...
2025-06-03 20:45:08 +03:00
WildAi
a879d15208
fix import
2025-06-02 20:26:05 +03:00
kijai
08a22951ed
Update nodes.py
2025-05-30 20:35:54 +03:00
kijai
9a52b7dfd2
Update image_nodes.py
2025-05-29 20:35:18 +03:00
kijai
b95b79ee82
Fix lora block loading
2025-05-28 14:31:22 +03:00
kijai
37eb7bddcb
Change Flux block lora loaderr into generic DiT lora block loader and support Wan with it
2025-05-28 12:57:17 +03:00
kijai
07b804cb3f
Add TorchCompileModelWanVideoV2
2025-05-21 17:38:22 +03:00
kijai
16f60e53e5
Add TorchCompileModelFluxAdvancedV2
...
Utilizing new ComfyUI core functions that also support LoRAs without additional patches
2025-05-21 17:17:41 +03:00
kijai
44565e9bff
Add choice of device for imageresize
2025-05-20 16:50:55 +03:00
kijai
aca7916352
Add modes to not do interpolation with CreateFadeMaskAdvanced
2025-05-20 16:50:42 +03:00
kijai
bec42252c6
smarter sage patch
2025-05-07 19:08:25 +03:00
kijai
ca07b9dadc
Add ModelPatchTorchSettings
2025-05-07 19:00:45 +03:00
kijai
6a35eefdd5
Update model_optimization_nodes.py
2025-05-07 17:52:47 +03:00
kijai
bfb6d973fe
update CheckpointLoaderKJ
2025-05-07 17:30:38 +03:00
kijai
b7e5b6f1e2
Default to center crop on the deprecated resize node
2025-05-05 21:54:34 +03:00
kijai
c3f0a55adf
Deprecate ImageResizeKJ and add ImageResizeKJ v2
...
Due to ComfyUI frontend changes the old node doesn't make that much sense anymore, and has issues between workflows saved with different versions of the front end.
2025-04-24 14:11:17 +03:00
kijai
086ac449a2
Update model_optimization_nodes.py
2025-04-23 20:09:09 +03:00