Yuki Shindo
2616c20687
fix embeddings path ( #237 )
2024-02-13 19:48:06 -05:00
Chenlei Hu
9c5038c766
Add --forge-ref-a1111-home cmd arg to reference existing A1111 checkout ( #203 )
...
* Add --forge-ref-a1111-home cmd arg to reference existing A1111 checkout
* nit
2024-02-11 21:22:31 -05:00
lllyasviel
30c8d742b3
Merge branch 'main' into upt
2024-02-11 16:42:36 -08:00
AUTOMATIC1111
b7f45e67dc
add before_token_counter callback and use it for prompt comments
2024-02-11 12:56:53 +03:00
AUTOMATIC1111
02ab75b86a
Count tokens of enabled styles
2024-02-11 12:40:27 +03:00
AUTOMATIC1111
f6e476d7a8
call the right function for token counter in img2img
2024-02-11 12:24:02 +03:00
AUTOMATIC1111
b531b0bbef
add propmpt comments support
2024-02-11 12:23:21 +03:00
AUTOMATIC1111
e2b19900ec
add infotext entry for emphasis; put emphasis into a separate file, add an option to parse but still ignore emphasis
2024-02-11 09:39:51 +03:00
AUTOMATIC1111
3732cf2f97
Merge pull request #14874 from hako-mikan/master
...
Add option to disable normalize embeddings after after calculating emphasis.
2024-02-11 08:34:40 +03:00
AUTOMATIC1111
860534399b
Merge pull request #14879 from AUTOMATIC1111/walk_files-extensions-case-insensitive
...
util.walk_files extensions case insensitive
2024-02-11 08:29:05 +03:00
AUTOMATIC1111
5ddd5d29e5
Merge pull request #14884 from light-and-ray/ResizeHandleRow_png_info_and_train
...
ResizeHandleRow png_info and train
2024-02-11 08:26:20 +03:00
AUTOMATIC1111
440fff64a2
Merge pull request #14890 from AUTOMATIC1111/always-append-timestamp
...
Always add timestamp to displayed image
2024-02-11 08:26:00 +03:00
lllyasviel
ee023f4fbf
Fix UniPC data cast and shape broadcast in #184
...
Fix UniPC data cast and shape broadcast in #184
This also fix potential problems in DDIM. The cause of this BUG is A1111’s `modules\models\diffusion\uni_pc\uni_pc.py` does not have a data cast and the Forge’s DDIM estimator forget to match the broadcast shape of sigmas.
(At the same time when we are fixing this BUG in A1111’s very original and high-quality samplers, comfyanonymous is still believing that Forge is using comfyui to sample images, eg, ComfyUI UniPC.
Comfyanonymous is so cute.
See also the jokes here https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/169#discussioncomment-8428689 )
2024-02-10 18:35:42 -08:00
missionfloyd
c04c4b95de
Always add timestamp to displayed image
2024-02-10 14:49:08 -07:00
Andray
82e2e25325
ResizeHandleRow png_info and train
2024-02-10 13:00:16 +04:00
Chenlei Hu
5a7e755528
ControlNet API ( #162 )
...
* ControlNet API
* update cache key
* nits
* disable controlnet tests
2024-02-10 01:16:13 -05:00
lllyasviel
bd0878754c
apply loras to refiner like upstream #161
2024-02-09 21:40:19 -08:00
lllyasviel
8059533eaf
fix lora not loaded for text encoder #142
2024-02-09 13:50:50 -08:00
Chenlei Hu
200f2b69ed
Add back ControlNet model version filter ( #131 )
...
* Add back ControlNet model version filter
* Update choice after sd model changes
2024-02-09 16:34:09 -05:00
Andray
e8f51579cc
add button for refreshing extensions list
2024-02-09 13:12:14 -08:00
w-e-w
542611cce4
walk_files extensions case insensitive
2024-02-10 05:39:01 +09:00
hako-mikan
c3c88ca8b4
Update sd_hijack_clip.py
2024-02-10 00:18:08 +09:00
hako-mikan
6b3f7039b6
add option
2024-02-09 23:57:46 +09:00
AUTOMATIC1111
d69a7944c9
Merge pull request #14857 from light-and-ray/refresh_extensions_list
...
Button for refresh extensions list
2024-02-09 16:06:02 +03:00
Chenlei Hu
3c32cbb0af
Revert "Fix more ruff lint ( #139 )" ( #144 )
...
This reverts commit e13072cb42
2024-02-08 21:34:58 -05:00
Chenlei Hu
388ca351f4
Revert "Fix ruff linter ( #137 )" ( #143 )
...
This reverts commit 6b3ad64388
2024-02-08 21:24:04 -05:00
Chenlei Hu
e13072cb42
Fix more ruff lint ( #139 )
2024-02-08 20:41:38 -05:00
Chenlei Hu
6b3ad64388
Fix ruff linter ( #137 )
...
* Fix ruff linter
* Remove unused imports
* Remove unused imports
2024-02-08 20:35:20 -05:00
lllyasviel
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
lllyasviel
760f727eb9
use better context manager to fix potential problems
2024-02-08 01:51:18 -08:00
Andray
99c6c4a51b
add button for refreshing extensions list
2024-02-07 16:06:17 +04:00
lllyasviel
257ac2653a
rework sigma device mapping
2024-02-07 00:44:12 -08:00
lllyasviel
d11c9d7506
fix sigmas device in rare cases #71
2024-02-06 23:12:35 -08:00
lllyasviel
4ea4a92fe9
fix inpaint batch dim align #94
2024-02-06 22:57:53 -08:00
lllyasviel
e579fab4d0
try solve #71
2024-02-06 17:46:23 -08:00
Chenlei Hu
79e4e46061
🐛 Fix SVD tab ( #63 )
2024-02-06 11:10:47 -05:00
lllyasviel
d76b830add
reduce prints
2024-02-06 07:56:15 -08:00
lllyasviel
1ecbff15fa
add note about token merging
2024-02-05 21:55:59 -08:00
lllyasviel
58dff34084
fix ddpm
2024-02-05 20:12:17 -08:00
lllyasviel
d45066bef5
Update rng.py
2024-02-05 14:12:31 -08:00
lllyasviel
b174caa275
Update rng.py
2024-02-05 14:08:34 -08:00
lllyasviel
1b9734c45b
Update rng.py
2024-02-05 13:50:19 -08:00
lllyasviel
8de4896bd6
fix inpaint formulation
2024-02-05 13:44:31 -08:00
lllyasviel
f5b3fcc6cf
Update rng.py
2024-02-05 13:33:27 -08:00
lllyasviel
0ba407fd9c
new samplers
...
DDPM
DDPM Karras
DPM++ 2M Turbo
DPM++ 2M SDE Turbo
LCM Karras
2024-02-05 03:58:06 -08:00
lllyasviel
049020f3c5
smaller default model
2024-02-04 18:54:50 -08:00
lllyasviel
27d815618d
remove xformer prints
2024-02-04 18:27:25 -08:00
Chenlei Hu
8117d7fcee
Add button to send generated image to svd tab ( #38 )
2024-02-04 18:22:56 -05:00
lllyasviel
2954a36c18
fix ldsr
2024-02-04 14:30:58 -08:00
lllyasviel
54d12ef989
ddim
2024-02-04 13:47:31 -08:00
