comfyanonymous
d0ec0081c4
Add block replace transformer_options to flux.
2024-11-12 08:00:39 -05:00
comfyanonymous
24432ca567
Allow 1D masks for 1D latents.
2024-11-11 14:44:52 -05:00
comfyanonymous
6042e06634
Support auto detecting some zsnr anime checkpoints.
2024-11-11 05:34:11 -05:00
comfyanonymous
33a428bb98
Refactor so that zsnr can be set in the sampling_settings.
2024-11-11 04:55:56 -05:00
comfyanonymous
d17896bfe8
Fast previews for mochi.
2024-11-10 03:39:35 -05:00
comfyanonymous
89be35ac18
Properly handle and reshape masks when used on 3d latents.
2024-11-09 15:30:19 -05:00
comfyanonymous
b236908ce4
Free memory before doing tiled decode.
2024-11-07 04:01:24 -05:00
comfyanonymous
6bef072519
Make VAEDecodeTiled node work with video VAEs.
2024-11-07 03:47:12 -05:00
comfyanonymous
c8a662055f
Remove scaled_fp8 key after reading it to silence warning.
2024-11-06 04:56:42 -05:00
comfyanonymous
cfe443b8e7
Fix unknown VAE being detected as the mochi VAE.
2024-11-05 03:43:27 -05:00
contentis
5599cf46c9
fix dynamic shape export ( #5490 )
2024-11-04 14:59:28 -05:00
comfyanonymous
cf71379da3
Fix mochi all in one checkpoint t5xxl key names.
2024-11-03 01:40:42 -05:00
comfyanonymous
0e63952db1
Mochi VAE encoder.
2024-11-01 17:33:09 -04:00
Aarni Koskela
b1f3e4513d
Avoid SyntaxWarning in UniPC docstring ( #5442 )
2024-10-31 15:17:26 -04:00
comfyanonymous
c1473e99c8
Bump up mac version for attention upcast bug workaround.
2024-10-31 15:15:31 -04:00
comfyanonymous
cac8491874
Fix diffusers flux controlnet regression.
2024-10-30 13:11:34 -04:00
comfyanonymous
44416ad2e5
Support SD3.5 medium diffusers format weights and loras.
2024-10-30 04:24:00 -04:00
comfyanonymous
0950eff963
Add a way to patch blocks in SD3.
2024-10-29 00:48:32 -04:00
comfyanonymous
013f30bae9
Update SD3 code.
2024-10-28 21:58:52 -04:00
comfyanonymous
c8815960f6
Remove useless line.
2024-10-28 17:41:12 -04:00
comfyanonymous
4a8865c14d
Set default shift on mochi to 6.0
2024-10-27 22:21:04 -04:00
comfyanonymous
1a27859ed1
float16 inference is a bit broken on mochi.
2024-10-27 04:56:40 -04:00
comfyanonymous
9f8e7912ef
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
5bbe9b0efe
Make LatentUpscale nodes work on 3d latents.
2024-10-26 01:50:51 -04:00
comfyanonymous
d3c29b6c15
Make euler_ancestral work on flow models (credit: Ashen).
2024-10-25 19:53:44 -04:00
PsychoLogicAu
567116a166
support SimpleTuner lycoris lora for SD3 ( #5340 )
2024-10-24 01:18:32 -04:00
comfyanonymous
de6f50a9d5
Fix ControlLora issue with last commit.
2024-10-23 17:02:40 -04:00
comfyanonymous
30d7a3db4f
Clean up some controlnet code.
...
Remove self.device which was useless.
2024-10-23 14:19:05 -04:00
comfyanonymous
0474115c2a
Fix lowvram edge case.
2024-10-22 16:34:50 -04:00
contentis
e828617856
remove attention abstraction ( #5324 )
2024-10-22 14:02:38 -04:00
comfyanonymous
46dbfc6b5c
Optimizations to --fast and scaled fp8.
2024-10-22 02:12:28 -04:00
comfyanonymous
e74b599f75
Fix duplicate sigmas on beta scheduler.
2024-10-21 20:19:45 -04:00
comfyanonymous
215cf1d843
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
comfyanonymous
567711396b
Support scaled fp8 t5xxl model.
2024-10-20 22:27:00 -04:00
comfyanonymous
ec9b115f28
Fixed model merging issue with scaled fp8.
2024-10-20 06:24:31 -04:00
comfyanonymous
adfa061b98
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
comfyanonymous
077a32ca01
Support diffusion models with scaled fp8 weights.
2024-10-19 23:47:42 -04:00
comfyanonymous
0f66e42b75
Clamp output when rounding weight to prevent Nan.
2024-10-19 19:07:10 -04:00
comfyanonymous
90105ed662
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
comfyanonymous
1ee9bd22e9
Revert "Fix Transformers FutureWarning ( #5140 )"
...
This reverts commit 2d77c6fec951bb8077fca6b3894d1d2153cc300d.
2024-10-16 12:36:19 -04:00
comfyanonymous
3eeaf6f13f
Cleanup some useless lines.
2024-10-14 21:02:39 -04:00
svdc
2d77c6fec9
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
comfyanonymous
0343a551e4
Fix fp8 ops staying enabled.
2024-10-12 14:10:13 -04:00
comfyanonymous
36ffa50637
Remove useless argument.
2024-10-12 07:16:21 -04:00
comfyanonymous
e931ff67d3
model_options consistency between functions.
...
weight_dtype -> dtype
2024-10-11 20:51:19 -04:00
Kadir Nar
9871047313
🐛 Add device to variable c ( #5210 )
2024-10-11 20:37:50 -04:00
comfyanonymous
3e7430aaa6
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
Dr.Lt.Data
b0d10d28bd
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
f792d1ce70
Increase maximum macOS version to 15.0.1 when forcing upcast attention ( #5191 )
2024-10-09 22:21:41 -04:00
comfyanonymous
6b0d97384c
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
