comfyanonymous
4514807781
Don't auto convert clip and vae weights to fp16 when saving checkpoint.
2024-06-12 01:07:58 -04:00
comfyanonymous
4a6dfb619d
SD3 better memory usage estimation.
2024-06-12 00:49:00 -04:00
comfyanonymous
9d4f62e30d
Single and dual clip loader nodes support SD3.
...
You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.
2024-06-11 23:27:39 -04:00
comfyanonymous
917810a2c6
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
2024-06-11 17:03:26 -04:00
comfyanonymous
c7e715e64a
Support multiple text encoder configurations on SD3.
2024-06-11 13:14:43 -04:00
comfyanonymous
0f719c05f1
Reuse code.
2024-06-11 07:20:26 -04:00
Dango233
8c3b1af91f
Remove redundancy in mmdit.py ( #3685 )
2024-06-11 06:30:25 -04:00
comfyanonymous
71ed9026b0
Fix bug with cosxl edit model.
2024-06-10 16:00:03 -04:00
comfyanonymous
cc2f32af2c
SD3 Support.
2024-06-10 14:06:23 -04:00
comfyanonymous
258e685fcc
Support sampling non 2D latents.
2024-06-10 01:31:09 -04:00
comfyanonymous
a2a20c27f4
Support zeroing out text embeddings with the attention mask.
2024-06-09 16:51:58 -04:00
comfyanonymous
372b1130d1
Reshape the empty latent image to the right amount of channels if needed.
2024-06-08 02:35:08 -04:00
comfyanonymous
add86d4eb5
Use the end token for the text encoder attention mask.
2024-06-07 03:05:23 -04:00
comfyanonymous
b6a9851535
Add function to get the list of currently loaded models.
2024-06-05 23:25:16 -04:00
comfyanonymous
20f463902f
pytorch xpu should be flash or mem efficient attention?
2024-06-04 17:44:14 -04:00
comfyanonymous
5eb529ced1
Remove useless code.
2024-06-02 19:23:37 -04:00
comfyanonymous
5f826c9921
Add an annoying print to a function I want to remove.
2024-06-01 12:47:31 -04:00
comfyanonymous
9cea5b91a0
Disable non_blocking when --deterministic or directml.
2024-05-30 11:07:38 -04:00
JettHu
0c313cb9ca
Fix UnetParams annotation typo ( #3589 )
2024-05-27 19:30:35 -04:00
comfyanonymous
93094050bb
Remove some unused imports.
2024-05-27 19:08:27 -04:00
comfyanonymous
358f3230d4
Fix DORA strength.
...
This is a different version of #3298 with more correct behavior.
2024-05-25 02:50:11 -04:00
comfyanonymous
8ece946997
Reduce memory usage when applying DORA: #3557
2024-05-24 23:36:48 -04:00
comfyanonymous
94a508adc2
Fix OSX latent2rgb previews.
2024-05-22 13:56:28 -04:00
Chenlei Hu
cc9c2a3144
Add type annotation UnetWrapperFunction ( #3531 )
...
* Add type annotation UnetWrapperFunction
* nit
* Add types.py
2024-05-22 02:07:27 -04:00
comfyanonymous
bdbaa4491c
Work around black image bug on Mac 14.5 by forcing attention upcasting.
2024-05-21 16:56:33 -04:00
comfyanonymous
e0c00cac39
Disable xformers when tracing model.
2024-05-21 13:55:49 -04:00
comfyanonymous
a8c173cc1b
Fix potential issue.
2024-05-20 08:19:54 -04:00
comfyanonymous
bcc5cd02c7
Log the pytorch version.
2024-05-20 06:22:29 -04:00
comfyanonymous
fc6cc5fafc
Fix controlnet not upcasting on models that have it enabled.
2024-05-19 17:58:03 -04:00
comfyanonymous
c19335f030
Cleanup.
2024-05-18 10:11:44 -04:00
comfyanonymous
fddf60ebb7
Remove unnecessary code.
2024-05-18 09:36:44 -04:00
comfyanonymous
367f84be8d
Don't automatically switch to lowvram mode on GPUs with low memory.
2024-05-17 00:31:32 -04:00
comfyanonymous
e2d71cc7b6
Add debug options to force on and off attention upcasting.
2024-05-16 04:09:41 -04:00
comfyanonymous
affe07f17d
Fix lowvram dora issue.
2024-05-15 02:47:40 -04:00
comfyanonymous
e02598e417
Fix SAG.
2024-05-14 18:02:27 -04:00
comfyanonymous
d4db823cfe
Only enable attention upcasting on models that actually need it.
2024-05-14 17:00:50 -04:00
comfyanonymous
89e38bcd63
Refactor attention upcasting code part 1.
2024-05-14 12:47:31 -04:00
Simon Lui
4cd1bc2cce
Fix Intel GPU memory allocation accuracy and documentation update. ( #3459 )
...
* Change calculation of memory total to be more accurate, allocated is actually smaller than reserved.
* Update README.md install documentation for Intel GPUs.
2024-05-12 06:36:30 -04:00
comfyanonymous
43079b39cd
Fix lowvram issue with saving checkpoints.
...
The previous fix didn't cover the case where the model was loaded in
lowvram mode right before.
2024-05-12 06:13:45 -04:00
comfyanonymous
397b840846
No longer necessary.
2024-05-12 05:34:43 -04:00
comfyanonymous
ae31a1b885
Fix issue with lowvram mode breaking model saving.
2024-05-11 21:55:20 -04:00
comfyanonymous
c655ec59dc
Remove warnings that confuse people.
2024-05-09 05:29:42 -04:00
comfyanonymous
bcc865f6ac
Typo fix.
2024-05-08 18:36:56 -04:00
comfyanonymous
d90e593478
Make the load checkpoint with config function call the regular one.
...
I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.
The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.
2024-05-06 20:04:39 -04:00
Simon Lui
87e7b35146
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
2024-05-02 03:26:50 -04:00
comfyanonymous
b04267ce30
Fix some edge cases with samplers and arrays with a single sigma.
2024-05-01 17:05:30 -04:00
comfyanonymous
95e80c5df1
Workaround xformers bug.
2024-04-30 21:23:40 -04:00
Garrett Sutula
533ddd78a0
Add TLS Support ( #3312 )
...
* Add TLS Support
* Add to readme
* Add guidance for windows users on generating certificates
* Add guidance for windows users on generating certificates
* Fix typo
2024-04-30 20:17:02 -04:00
Jedrzej Kosinski
7a37c3088d
Fix error when more cond masks passed in than batch size ( #3353 )
2024-04-26 12:51:12 -04:00
comfyanonymous
e7cd70ed48
Don't init a VAE model when there are no VAE weights.
2024-04-24 09:20:31 -04:00
