patientx
0575f60ac4
Merge branch 'comfyanonymous:master' into master
2024-10-26 15:10:27 +03:00
comfyanonymous
5cbb01bc2f
Basic Genmo Mochi video model support.
...
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.
EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
2024-10-26 06:54:00 -04:00
comfyanonymous
c3ffbae067
Make LatentUpscale nodes work on 3d latents.
2024-10-26 01:50:51 -04:00
comfyanonymous
d605677b33
Make euler_ancestral work on flow models (credit: Ashen).
2024-10-25 19:53:44 -04:00
patientx
6a9115d7ea
Merge branch 'comfyanonymous:master' into master
2024-10-24 11:06:56 +03:00
PsychoLogicAu
af8cf79a2d
support SimpleTuner lycoris lora for SD3 ( #5340 )
2024-10-24 01:18:32 -04:00
patientx
bb7e9ef812
Merge branch 'comfyanonymous:master' into master
2024-10-24 00:06:13 +03:00
comfyanonymous
66b0961a46
Fix ControlLora issue with last commit.
2024-10-23 17:02:40 -04:00
patientx
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
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
5a8a48931a
remove attention abstraction ( #5324 )
2024-10-22 14:02:38 -04:00
patientx
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
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
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
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
d4b509799f
Merge branch 'comfyanonymous:master' into master
2024-10-18 11:14:20 +03:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
patientx
fc4acf26c3
Merge branch 'comfyanonymous:master' into master
2024-10-16 23:54:39 +03:00
comfyanonymous
0bedfb26af
Revert "Fix Transformers FutureWarning ( #5140 )"
...
This reverts commit 95b7cf9bbe
2024-10-16 12:36:19 -04:00
patientx
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
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
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
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
ad07796777
🐛 Add device to variable c ( #5210 )
2024-10-11 20:37:50 -04:00
patientx
e4d24788f1
Merge branch 'comfyanonymous:master' into master
2024-10-11 00:22:45 +03:00
comfyanonymous
1b80895285
Make clip loader nodes support loading sd3 t5xxl in lower precision.
...
Add attention mask support in the SD3 text encoder code.
2024-10-10 15:06:15 -04:00
patientx
f9eab05f54
Merge branch 'comfyanonymous:master' into master
2024-10-10 10:30:17 +03:00
Dr.Lt.Data
5f9d5a244b
Hotfix for the div zero occurrence when memory_used_encode is 0 ( #5121 )
...
https://github.com/comfyanonymous/ComfyUI/issues/5069#issuecomment-2382656368
2024-10-09 23:34:34 -04:00
Jonathan Avila
4b2f0d9413
Increase maximum macOS version to 15.0.1 when forcing upcast attention ( #5191 )
2024-10-09 22:21:41 -04:00
comfyanonymous
e38c94228b
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
...
This is used to load weights in fp8 and use fp8 matrix multiplication.
2024-10-09 19:43:17 -04:00
patientx
21d9bef158
Merge branch 'comfyanonymous:master' into master
2024-10-09 11:22:05 +03:00
comfyanonymous
203942c8b2
Fix flux doras with diffusers keys.
2024-10-08 19:03:40 -04:00
patientx
df174b7cbd
Merge branch 'comfyanonymous:master' into master
2024-10-07 22:22:38 +03:00
comfyanonymous
8dfa0cc552
Make SD3 fast previews a little better.
2024-10-07 09:19:59 -04:00
patientx
445390eae2
Merge branch 'comfyanonymous:master' into master
2024-10-07 10:15:48 +03:00
comfyanonymous
e5ecdfdd2d
Make fast previews for SDXL a little better by adding a bias.
2024-10-06 19:27:04 -04:00
