lllyasviel/stable-diffusion-webui-forge
1
0
Fork 0
mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2026-02-05 15:39:59 +00:00
Code Issues Packages Projects Releases Wiki Activity
8,410 Commits 3 Branches 3 Tags
15f41b2e5e81f86ef4e32f0abaabc83320d73bc9
Commit Graph

8410 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
layerdiffusion
15f41b2e5e we do not need initial model download now 
since we do not load model when UI start
 2024-08-27 17:59:56 -07:00
layerdiffusion
20cdcf05f5 experimental: allow some tabs to hide model bar 2024-08-27 17:45:44 -07:00
layerdiffusion
db6448df74 Update Status 2024-08-27 08:34:53 -07:00
layerdiffusion
9c03493262 add some misc fix related to info text 2024-08-27 07:51:28 -07:00
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
DenOfEquity
3c4eb78cd1 Merge pull request #1531 from DenOfEquity/fix-the-hrfix-fix 
Update txt2img.py: fix the hrfix fix
 2024-08-27 00:55:42 +01:00
DenOfEquity
d7b8127438 Update txt2img.py: fix the hrfix fix 
main issue: Upscaling would fail on single image when controlnet used.

minor issues: On the way to fixing my oversight of not accounting for control images in the gallery, I found that attempting to upscale a control image would fail due to trying to access infotext that doesn't exist. Then I handled a case previously caught by an assert more gracefully. Unhandled, these minor issues would lose the current gallery, so these extra fixes are good QoL.
Then I found another related minor issue if grids are not displayed.
 2024-08-27 00:40:21 +01:00
layerdiffusion
18b356c0dc fix 2024-08-26 16:15:07 -07:00
cluder
e94130a82a Fix Checkpoint Merging #1359,#1095 (#1454) 
- checkpoint_list[] contains the CheckpointInfo.title which is "checkpointname.safetensor [hash]"
  when a checkpoint is selected to be loaded during merge, we try to match it with just "checkpointname.safetensor".
  -> use checkpoint_aliases[] which already contains the checkpoint key in all possible variants.
- replaced removed sd_models.read_state_dict() with sd_models.load_torch_file()
- replaced removed sd_vae.load_vae_dict() with sd_vae.load_torch_file()
- uncommented create_config() for now, since it calls a removed method: sd_models_config.find_checkpoint_config_near_filename()
 2024-08-26 15:39:37 -07:00
altoiddealer
d55e6b5bfe Replace API sd-vae with sd-modules (#1463) 2024-08-26 15:08:02 -07:00
DenOfEquity
230e39110e Merge pull request #1492 from DenOfEquity/restore-postprocessing_focal_crop-script 
Restore postprocessing_focal_crop script
 2024-08-26 16:19:07 +01:00
DenOfEquity
37d8f87ae9 Merge pull request #1507 from DenOfEquity/cmd-arg-for-text-encoders 
add startup argument for text encoders location
 2024-08-26 15:50:21 +01:00
layerdiffusion
acf99dd74e fix old version of pytorch 2024-08-26 06:51:48 -07:00
layerdiffusion
f22b80ef94 restrict baking to 16bits 2024-08-26 06:16:13 -07:00
layerdiffusion
7cd94babdd Revert "Update README.md" 
This reverts commit 891e355fc8.
 2024-08-26 04:52:46 -07:00
DenOfEquity
0a1fb97679 Merge branch 'lllyasviel:main' into cmd-arg-for-text-encoders 2024-08-26 11:28:00 +01:00
DenOfEquity
a0e317518e update cmd_args.py: description 
extra description for old clip argument
 2024-08-26 11:27:35 +01:00
layerdiffusion
388b70134b fix offline loras 2024-08-25 20:28:40 -07:00
lllyasviel
891e355fc8 Update README.md 2024-08-25 17:38:54 -07:00
layerdiffusion
b25b62da96 fix T5 not baked 2024-08-25 17:31:50 -07:00
layerdiffusion
cae37a2725 fix dequant of unbaked parameters 2024-08-25 17:24:31 -07:00
layerdiffusion
82dfc2b15b Significantly speed up Q4_0, Q4_1, Q4_K 
by precomputing all possible 4bit dequant into a lookup table and use pytorch indexing to get dequant, rather than really computing the bit operations.
This should give very similar performance to native CUDA kernels, while being LoRA friendly and more flexiable
 2024-08-25 16:49:33 -07:00
layerdiffusion
e60bb1c96f Make Q4_K_S as fast as Q4_0 
by baking the layer when model load
 2024-08-25 15:02:54 -07:00
layerdiffusion
868f662eb6 fix 2024-08-25 14:44:01 -07:00
layerdiffusion
13d6f8ed90 revise GGUF by precomputing some parameters 
rather than computing them in each diffusion iteration
 2024-08-25 14:30:09 -07:00
Panchovix
ba01ad3711 Merge pull request #1489 from DenOfEquity/pnginfo 
allow repeated drag-drop into PNGInfo tab
 2024-08-25 16:27:39 -04:00
DenOfEquity
001f2305de Update cmd_args.py: add text-encoder-dir 2024-08-25 15:03:02 +01:00
DenOfEquity
8c6b64e6e9 main_entry.py: add support for new text_encoder_dir cmd arg 
copying method used for VAE
 2024-08-25 15:01:30 +01:00
DenOfEquity
187faf3c5a restore postprocessing_focal_crop.py 
with one line fix - convert input image to RGB
 2024-08-25 13:24:55 +01:00
DenOfEquity
fc9b80cf0e restore autocrop.py 2024-08-25 13:23:21 +01:00
DenOfEquity
424baa110d Update dragdrop.js 
remove unnecessary check for PNGInfo element
enables repeated drag-drop into PNG Info
fixes https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/1485
 2024-08-25 10:14:45 +01:00
Panchovix
59dd981fa7 Merge pull request #1484 from altoiddealer/api_get_extensions_commit_date 
Correct commit_date type to 'int'
 2024-08-24 22:43:26 -04:00
altoiddealer
7dde12e5cf Correct commit_date type to 'int' 2024-08-24 21:17:08 -04:00
lllyasviel
f82029c5cf support more t5 quants (#1482) 
lets hope this is the last time that people randomly invent new state dict key formats
 2024-08-24 12:47:49 -07:00
lllyasviel
0f3309eb3d Add doc 2024-08-24 02:07:13 -07:00
layerdiffusion
8ff0dc6fed add quick list 2024-08-23 11:43:34 -07:00
altoiddealer
86e3ccaa9d checkpoint change (#1427) 
* checkpoint change

credit to @dermesut

https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/1421

Enables `sd_model_checkpoint` parameter for API payloads

* Omit redundant .save()
 2024-08-23 09:01:30 -07:00
layerdiffusion
f23ee63cb3 always set empty cache signal as long as any patch happens 2024-08-23 08:56:57 -07:00
layerdiffusion
df598c4df5 add "Diffusion in Low Bits" to info text 2024-08-22 23:23:14 -07:00
layerdiffusion
0bf68c5448 revise NGMS 2024-08-22 23:07:05 -07:00
Haoming
7b3b5fd0fd ngms (#1434) 2024-08-22 23:06:17 -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
Will Cole
088be3af0e Possible partial fix for #952, #1235, #1343 (#1386) 2024-08-22 21:48:08 -07:00
twarrendewit
f7ab23b1cb Variable-Strength StyleAlign (#1387) 
* adding efficiency

* adding variable strength

* Revert "adding efficiency"

This reverts commit 6d0ad98c06.

* updating with 0 and 1 cases

---------

Co-authored-by: T. Warren de Wit <tww0007@uah.edu>
 2024-08-22 12:52:41 -07:00
altoiddealer
d169cd5881 Gets type (#1410) 2024-08-22 12:50:09 -07:00
layerdiffusion
2ab19f7f1c revise lora patching 2024-08-22 11:59:43 -07:00
DenOfEquity
28ad046447 add distilled cfg to xyz grid (#1413) 2024-08-22 10:53:32 -07:00
layerdiffusion
68bf7f85aa speed up nf4 lora in offline patching mode 2024-08-22 10:35:11 -07:00
layerdiffusion
95d04e5c8f fix 2024-08-22 10:08:21 -07:00
layerdiffusion
14eac6f2cf add a way to empty cuda cache on the fly 2024-08-22 10:06:39 -07:00