847d451505
Fix command line arguments format in webui-user.bat ( #135 )
...
* fix command line arguments format in webui-user.bat
* fix embeddings dir path
2024-02-08 19:47:42 -05:00
f06ba8e60b
Significantly reduce thread abuse for faster model moving
...
This will move all major gradio calls into the main thread rather than random gradio threads.
This ensures that all torch.module.to() are performed in main thread to completely possible avoid GPU fragments.
In my test now model moving is 0.7 ~ 1.2 seconds faster, which means all 6GB/8GB VRAM users will get 0.7 ~ 1.2 seconds faster per image on SDXL.
2024-02-08 10:13:59 -08:00
291ec743b6
use better context manager to fix potential problems
2024-02-08 02:00:54 -08:00
760f727eb9
use better context manager to fix potential problems
2024-02-08 01:51:18 -08:00
4c9db26541
support controlnet_model_function_wrapper for t2i-adapter
2024-02-07 21:42:56 -08:00
50035ad414
fix outpaint with inpaint_global_harmonious
2024-02-07 20:31:22 -08:00
49ec325f6a
lin
2024-02-07 20:14:02 -08:00
a1670c536d
Allow controlnet_model_function_wrapper
...
for animatediff to manage controlnet batch slicing window
2024-02-07 20:06:23 -08:00
383aaca1eb
Improve model filtering ( #114 )
2024-02-07 22:53:41 -05:00
42dd258c8d
revise attention alignment in stylealign #100
...
A mistake in 0day release is that the attention layers of cond and uncond items in a batch are aligned when they should not.
after align batch in cond and uncond separately they now works and give same results to legacy sd-webui-cnet
2024-02-07 19:11:53 -08:00
f63917a323
add codes discussed in #73 that may help ipadapters
2024-02-07 18:57:57 -08:00
ef781cabcb
Backend: Allow control signal to be none for advanced weighting
2024-02-07 13:02:42 -08:00
c3a66b016b
try solve dtype cast for #112
2024-02-07 12:39:55 -08:00
e1faf8327b
Add back ControlNet HR option ( #90 )
...
* Add back ControlNet HR option
* nits
* protect kernel
* add enum
* fix
* fix
* Update controlnet.py
* restore controlnet.py
* hint ui
* Update controlnet.py
* fix
* Update controlnet.py
* Backend: better controlnet mask batch broadcasting
* Update README.md
* fix inpaint batch dim align #94
* fix sigmas device in rare cases #71
* rework sigma device mapping
* Add hr_option to infotext
---------
Co-authored-by: lllyasviel <lyuminzhang@outlook.com >
2024-02-07 11:09:52 -05:00
257ac2653a
rework sigma device mapping
2024-02-07 00:44:12 -08:00
d11c9d7506
fix sigmas device in rare cases #71
2024-02-06 23:12:35 -08:00
4ea4a92fe9
fix inpaint batch dim align #94
2024-02-06 22:57:53 -08:00
65f9c7d442
Update README.md
2024-02-06 21:46:54 -08:00
c185e39e59
Backend: better controlnet mask batch broadcasting
2024-02-06 20:13:09 -08:00
1110183943
Fix ControlNet UI preset ( #87 )
2024-02-06 21:52:04 -05:00
e62631350a
Update forge_version.py
2024-02-06 17:55:14 -08:00
e579fab4d0
try solve #71
2024-02-06 17:46:23 -08:00
6301a6660e
solve #73
2024-02-06 17:28:00 -08:00
711844ecd8
solve #76
2024-02-06 17:25:28 -08:00
70ae2a4bce
fix controlnet ignored in batch #55
2024-02-06 17:12:57 -08:00
fc5c70a28d
gradio fix
2024-02-06 14:32:42 -08:00
b58b0bd425
batch mask ( #44 )
...
* mask batch, not working
* mask batch, working, infotext broken
* try remove old codes
* set CUDA_VISIBLE_DEVICES with args
* Revert "try remove old codes"
This reverts commit 63c527c373🐛 Fix infotext
---------
Co-authored-by: lllyasviel <lyuminzhang@outlook.com >
Co-authored-by: huchenlei <chenlei.hu@mail.utoronto.ca >
2024-02-06 12:54:35 -06:00
5bea443d94
add a note after fixing repeated loading bug on 4090
2024-02-06 08:13:29 -08:00
79e4e46061
🐛 Fix SVD tab ( #63 )
2024-02-06 11:10:47 -05:00
402b7beb87
fix repeated model loading bug on 4090
2024-02-06 08:02:03 -08:00
a578da074b
fix repeated model loading bug on 4090
2024-02-06 07:59:19 -08:00
d76b830add
reduce prints
2024-02-06 07:56:15 -08:00
65367aa24d
accurate words
2024-02-06 07:51:37 -08:00
4939cf18d8
update hints for 4090
2024-02-06 07:43:33 -08:00
7359740f36
Revert "safer device"
...
This reverts commit 1204d490d9
2024-02-06 05:27:07 -08:00
1204d490d9
safer device
2024-02-06 05:01:58 -08:00
9c31b0ddcb
try fix #56
2024-02-06 04:51:08 -08:00
6aee7a2032
Update forge_version.py
2024-02-05 23:55:27 -08:00
74ff4a9ba9
set CUDA_VISIBLE_DEVICES with args
2024-02-05 23:53:11 -08:00
1ecbff15fa
add note about token merging
2024-02-05 21:55:59 -08:00
7fd499a034
use new links for images if they were broken
2024-02-05 21:41:37 -08:00
b8cd6d2e21
Update forge_version.py
2024-02-05 20:12:37 -08:00
58dff34084
fix ddpm
2024-02-05 20:12:17 -08:00
393c19bbcf
Remove Lycoris back compact ( #41 )
...
Forge use totally different mechanism to handle lora/lycoris models
I think it is good to remove the back compact things so "lyco" alias can be used by legacy lycoris extensions. (some other extension may rely on it)
2024-02-06 11:17:15 +08:00
b03df6fdb1
Update README.md
2024-02-05 17:59:37 -08:00
f4e6794dbd
Update README.md
2024-02-05 17:13:47 -08:00
c5b51b35fb
Update README.md
2024-02-05 15:50:44 -08:00
218a10179b
Update README.md
2024-02-05 15:48:57 -08:00
4221ccf239
Update README.md
2024-02-05 15:45:03 -08:00
53057f33ed
Update forge_version.py
2024-02-05 15:30:45 -08:00
Yuki Shindo