comfyanonymous
52810907e2
Add a model merge node for SD3.5 large.
2024-10-24 16:46:21 -04:00
patientx and GitHub
6a9115d7ea
Merge branch 'comfyanonymous:master' into master
2024-10-24 11:06:56 +03:00
PsychoLogicAu and GitHub
af8cf79a2d
support SimpleTuner lycoris lora for SD3 ( #5340 )
2024-10-24 01:18:32 -04:00
patientx and GitHub
bb7e9ef812
Merge branch 'comfyanonymous:master' into master
2024-10-24 00:06:13 +03:00
patientx and GitHub
3b96468e0c
Update README.md
2024-10-24 00:05:42 +03:00
comfyanonymous
66b0961a46
Fix ControlLora issue with last commit.
2024-10-23 17:02:40 -04:00
patientx and GitHub
ca700c7638
Merge branch 'comfyanonymous:master' into master
2024-10-23 23:58:26 +03:00
comfyanonymous
754597c8a9
Clean up some controlnet code.
...
Remove self.device which was useless.
2024-10-23 14:19:05 -04:00
patientx and GitHub
fd143ca944
Merge branch 'comfyanonymous:master' into master
2024-10-23 00:19:39 +03:00
comfyanonymous
915fdb5745
Fix lowvram edge case.
2024-10-22 16:34:50 -04:00
contentis and GitHub
5a8a48931a
remove attention abstraction ( #5324 )
2024-10-22 14:02:38 -04:00
patientx and GitHub
f0e8767deb
Merge branch 'comfyanonymous:master' into master
2024-10-22 13:39:15 +03:00
comfyanonymous
8ce2a1052c
Optimizations to --fast and scaled fp8.
2024-10-22 02:12:28 -04:00
comfyanonymous
f82314fcfc
Fix duplicate sigmas on beta scheduler.
2024-10-21 20:19:45 -04:00
comfyanonymous
0075c6d096
Mixed precision diffusion models with scaled fp8.
...
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
2024-10-21 18:12:51 -04:00
patientx and GitHub
9fd46200ab
Merge branch 'comfyanonymous:master' into master
2024-10-21 12:23:49 +03:00
comfyanonymous
83ca891118
Support scaled fp8 t5xxl model.
2024-10-20 22:27:00 -04:00
patientx and GitHub
5a425aeda1
Merge branch 'comfyanonymous:master' into master
2024-10-20 21:06:24 +03:00
comfyanonymous
f9f9faface
Fixed model merging issue with scaled fp8.
2024-10-20 06:24:31 -04:00
patientx and GitHub
1678ea8f9c
Merge branch 'comfyanonymous:master' into master
2024-10-20 10:20:06 +03:00
comfyanonymous
471cd3eace
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
comfyanonymous
a68bbafddb
Support diffusion models with scaled fp8 weights.
2024-10-19 23:47:42 -04:00
comfyanonymous
73e3a9e676
Clamp output when rounding weight to prevent Nan.
2024-10-19 19:07:10 -04:00
patientx and GitHub
f1948ac144
Merge branch 'comfyanonymous:master' into master
2024-10-18 13:25:35 +03:00
comfyanonymous
518c0dc2fe
Add tooltips to LoraSave node.
2024-10-18 06:01:09 -04:00
patientx and GitHub
0c33561160
Update README.md
2024-10-18 11:14:57 +03:00
patientx and GitHub
d4b509799f
Merge branch 'comfyanonymous:master' into master
2024-10-18 11:14:20 +03:00
patientx and GitHub
93751fd1bd
Update README.md
2024-10-18 11:14:12 +03:00
comfyanonymous
ce0542e10b
Add a note that python 3.13 is not yet supported to the README.
2024-10-17 19:27:37 -04:00
comfyanonymous
8473019d40
Pytorch can be shipped with numpy 2 now.
2024-10-17 19:15:17 -04:00
89f15894dd
Ignore more network related errors during websocket communication. ( #5269 )
...
Intermittent network issues during websocket communication should not crash ComfyUi process.
Co-authored-by: Xiaodong Xie <xie.xiaodong@frever.com >
2024-10-17 18:31:45 -04:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
patientx and GitHub
fc4acf26c3
Merge branch 'comfyanonymous:master' into master
2024-10-16 23:54:39 +03:00
comfyanonymous
7390ff3b1e
Add missing import.
2024-10-16 14:58:30 -04:00
comfyanonymous
0bedfb26af
Revert "Fix Transformers FutureWarning ( #5140 )"
...
This reverts commit 95b7cf9bbe
2024-10-16 12:36:19 -04:00
comfyanonymous
f71cfd2687
Add an experimental node to sharpen latents.
...
Can be used with LatentApplyOperationCFG for interesting results.
2024-10-16 05:25:31 -04:00
Alex "mcmonkey" Goodwin and GitHub
c695c4af7f
Frontend Manager: avoid redundant gh calls for static versions ( #5152 )
...
* Frontend Manager: avoid redundant gh calls for static versions
* actually, removing old tmpdir isn't needed
I tested - downloader code handles this case well already
(also rmdir was wrong func anyway, needed shutil.rmtree if it had content)
* add code comment
2024-10-16 03:35:37 -04:00
patientx and GitHub
a67cb80d33
Merge branch 'comfyanonymous:master' into master
2024-10-15 23:43:46 +03:00
comfyanonymous
0dbba9f751
Add some latent operation nodes.
...
This is a port of the ModelSamplerTonemapNoiseTest from the experiments
repo.
To replicate that node use LatentOperationTonemapReinhard and
LatentApplyOperationCFG together.
2024-10-15 15:00:36 -04:00
patientx and GitHub
f143a803d6
Merge branch 'comfyanonymous:master' into master
2024-10-15 09:55:21 +03:00
comfyanonymous
f584758271
Cleanup some useless lines.
2024-10-14 21:02:39 -04:00
svdc and GitHub
95b7cf9bbe
Fix Transformers FutureWarning ( #5140 )
...
* Update sd1_clip.py
Fix Transformers FutureWarning
* Update sd1_clip.py
Fix comment
2024-10-14 20:12:20 -04:00
patientx and GitHub
b24af8b083
Merge branch 'comfyanonymous:master' into master
2024-10-13 23:35:06 +03:00
comfyanonymous
191a0d56b4
Switch default packaging workflows to python 3.12
2024-10-13 06:59:31 -04:00
patientx and GitHub
a5e3eae103
Merge branch 'comfyanonymous:master' into master
2024-10-12 23:00:55 +03:00
comfyanonymous
3c60ecd7a8
Fix fp8 ops staying enabled.
2024-10-12 14:10:13 -04:00
comfyanonymous
7ae6626723
Remove useless argument.
2024-10-12 07:16:21 -04:00
patientx and GitHub
eae1c15ab1
Merge branch 'comfyanonymous:master' into master
2024-10-12 11:02:28 +03:00
comfyanonymous
6632365e16
model_options consistency between functions.
...
weight_dtype -> dtype
2024-10-11 20:51:19 -04:00
Kadir Nar and GitHub
ad07796777
🐛 Add device to variable c ( #5210 )
2024-10-11 20:37:50 -04:00
comfyanonymous