DenOfEquity
d1e403619d
Add files via upload ( #1689 )
2024-09-05 19:20:21 +01:00
wcole3
05bdc3e44f
Remove dtype field
2024-09-02 13:06:30 -04:00
wcole3
ef112ae8d2
Cleanup
2024-09-02 12:38:31 -04:00
wcole3
dee7a3c287
Use computation_dtype instead of storage_dtype
2024-09-02 12:23:17 -04:00
wcole3
350018eff5
Set controlllite module dtype to model dtype
2024-09-02 09:52:13 -04:00
DenOfEquity
2c907b24c9
fix for Batch Upload (gallery)
...
now needs to check for None
2024-08-31 21:52:10 +01:00
layerdiffusion
3b9b2f653e
sapiens normal
...
- 100% reproduce all author results and demos
- 0.3b/0.6b/1b/2b models, all pass 2GB VRAM (powered by Forge backend memory system
- perfect memory management for quick shifting between other spaces or forge main UI
2024-08-30 17:34:30 -07:00
layerdiffusion
d1d0ec46aa
Maintain patching related
...
1. fix several problems related to layerdiffuse not unloaded
2. fix several problems related to Fooocus inpaint
3. Slightly speed up on-the-fly LoRAs by precomputing them to computation dtype
2024-08-30 15:18:21 -07:00
layerdiffusion
c239200705
fix
2024-08-29 19:18:40 -07:00
DenOfEquity
ea6d03bde1
fix #258
...
fix longstanding bug with Dyn Cfg Augmentation and batch >= 2 (#258 )
2024-08-29 00:45:52 +01:00
Lucas Freire Sangoi
d1121baf80
Adding Depth Anything v2 to ControlNet Integrated ( #1519 )
...
* Update install.py
adding install of depth anything v2
* Add files via upload
adding depth anything v2 preprocessor
* Update preprocessor_compiled.py
adding preprocessor
* Update preprocessor.py
adding preprocessor functions
2024-08-27 06:55:31 -07:00
Igor Aherne
4dc36268c2
bugfix: controlnet works in API - image no longer a dictionary ( #1425 )
...
Generating from browser works with controlnet.
Generating via API wasn't.
This is because from_dict() was making 'image' and 'mask_image' a dictionary.
In 'controlnet.py' function 'get_input_data' this would cause the following check to throw exception because used to be an incorrect type:
elif (unit_image < 5).all() and (unit_image_fg > 5).any():
Now, they are never a dictionary and check is fine
2024-08-22 21:50:33 -07:00
twarrendewit
f7ab23b1cb
Variable-Strength StyleAlign ( #1387 )
...
* adding efficiency
* adding variable strength
* Revert "adding efficiency"
This reverts commit 6d0ad98c06tww0007@uah.edu >
2024-08-22 12:52:41 -07:00
layerdiffusion
c1614e08c6
fix #1385
2024-08-21 22:08:07 -07:00
layerdiffusion
2b1e7366a7
Update requirements.txt
2024-08-21 03:31:24 -07:00
layerdiffusion
250ae27749
The First IDM-VTON that pass 4GB VRAM
...
100% reproduce official results
2024-08-20 21:30:47 -07:00
layerdiffusion
5452bc6ac3
All Forge Spaces Now Pass 4GB VRAM
...
and they all 100% reproduce author results
2024-08-20 08:01:10 -07:00
layerdiffusion
65ec461f8a
revise space
2024-08-19 22:43:09 -07:00
layerdiffusion
95bc586547
geowizard
2024-08-19 00:27:21 -07:00
layerdiffusion
631a097d0b
change Florence-2 default to base
2024-08-18 21:31:24 -07:00
layerdiffusion
ca2db770a9
ic light
2024-08-18 21:16:58 -07:00
layerdiffusion
4751d6646d
Florence-2
2024-08-18 20:51:44 -07:00
layerdiffusion
1cbd13c85a
Animagine XL 3.1 Official User Interface
2024-08-18 20:05:16 -07:00
layerdiffusion
da72cd6fab
IllusionDiffusion
2024-08-18 03:27:44 -07:00
layerdiffusion
2292f9a100
Technically Correct PhotoMaker V2
...
that can actually reproduce author results, and be used in serious research and writing academic papers
2024-08-18 01:47:27 -07:00
layerdiffusion
72ab92f83e
upload meta files
2024-08-18 00:12:53 -07:00
layerdiffusion
0ccbac5389
revise space logics
2024-08-18 00:04:02 -07:00
layerdiffusion
7df7ea3d6b
fix birefnet commit
2024-08-17 08:38:31 -07:00
lllyasviel
93b40f355e
Forge Space and BiRefNet
2024-08-17 08:29:08 -07:00
continue revolution
5fa8c6d414
remove basicsr ( #1214 )
2024-08-16 20:33:38 -07:00
layerdiffusion
dc7f92eb96
fix fooocus inpaint
2024-08-16 03:21:28 -07:00
layerdiffusion
12369669cf
only load lora one time
2024-08-16 02:02:22 -07:00
layerdiffusion
a0849953bd
revise
2024-08-13 15:13:39 -07:00
layerdiffusion
fb390f0b44
clean up
2024-08-11 23:06:00 -07:00
layerdiffusion
a91a81d8e6
revise structure
2024-08-07 20:44:34 -07:00
layerdiffusion
77a4980f08
remove everything related to training
2024-08-05 04:35:09 -07:00
layerdiffusion
bccf9fb23a
Free WebUI from its Prison
...
Congratulations WebUI. Say Hello to freedom.
2024-08-05 04:21:35 -07:00
layerdiffusion
aafe11b14c
Revert "Free WebUI from its Prison"
...
This reverts commit 62c11fdc71
2024-08-05 03:52:44 -07:00
layerdiffusion
62c11fdc71
Free WebUI from its Prison
...
Congratulations WebUI. Say Hello to freedom.
2024-08-05 03:39:54 -07:00
layerdiffusion
be3f0a0039
remove legacy config
2024-08-03 17:04:56 -07:00
layerdiffusion
8c087f920e
rename files
2024-08-03 15:54:39 -07:00
layerdiffusion
b8b29a2372
remove forge_sampler
2024-08-03 15:38:07 -07:00
layerdiffusion
a17abbc097
Update forge_stylealign.py
2024-08-03 14:49:40 -07:00
layerdiffusion
b3a6eeefd6
Update forge_sag.py
2024-08-03 14:49:02 -07:00
layerdiffusion
dfc3879a69
disable photomaker
...
PhotoMaker has significant degradation compared to Tencent official results because of ComfyUI's defective implementation
I will impl it and compare to Tencent official results later
2024-08-03 14:40:10 -07:00
layerdiffusion
6c2afbbbbd
Update forge_perturbed_attention.py
2024-08-03 14:37:36 -07:00
layerdiffusion
754a9d0480
Update forge_never_oom.py
2024-08-03 14:36:40 -07:00
layerdiffusion
4e4296b6fa
tiled diffusion
2024-08-03 14:32:47 -07:00
layerdiffusion
e6bd652a4a
lora and kohyafix
2024-08-03 14:24:38 -07:00
layerdiffusion
07b2d2ccac
clipvision, ipadapter, and misc
...
backend is 75% finished
2024-08-03 14:18:16 -07:00
