d8ahazard
e82ea20299
Optimize model loader
...
Child classes only get populated to __subclassess__ when they are imported. We don't actually need to import any of them to webui any more, so clean up webUI imports and make sure loader imports children.
Also, fix command line paths not actually being passed to the scalers.
2022-09-30 15:26:18 -05:00
AUTOMATIC
d1f098540a
remove unwanted formatting/functionality from the PR
2022-09-30 11:42:40 +03:00
d8ahazard
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-29 19:59:36 -05:00
d8ahazard
0dce0df1ee
Holy $hit.
...
Yep.
Fix gfpgan_model_arch requirement(s).
Add Upscaler base class, move from images.
Add a lot of methods to Upscaler.
Re-work all the child upscalers to be proper classes.
Add BSRGAN scaler.
Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff.
Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated.
Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size.
Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size.
Add typehints for IDE sanity.
PEP-8 improvements.
Moar.
2022-09-29 17:46:23 -05:00
AUTOMATIC
2f2d356e4c
call torch_gc before/after each gpu gradio operation
2022-09-29 11:32:12 +03:00
d8ahazard
5756d517a6
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-27 11:02:41 -05:00
d8ahazard
11875f5863
Use model loader with stable-diffusion too.
...
Hook the model loader into the SD_models file.
Add default url/download if checkpoint is not found.
Add matching stablediffusion-models-path argument.
Add message that --ckpt-dir will be removed in the future, but have it pipe to stablediffusion-models-path for now.
Update help strings for models-path args so they're more or less uniform.
Move sd_model "setup" call to webUI with the others.
Ensure "cleanup_models" method moves existing models to the new locations, including SD, and that we aren't deleting folders that still have stuff in them.
2022-09-27 11:01:13 -05:00
d8ahazard
7d5c29b674
Cleanup existing directories, fixes
2022-09-26 10:27:18 -05:00
d8ahazard
740070ea9c
Re-implement universal model loading
2022-09-26 09:29:50 -05:00
William Moorehouse
91643f651d
Add support for checkpoint merging
2022-09-25 19:22:12 -04:00
Eyrie
1877a3767e
Changed job_id to timestamp
2022-09-25 17:11:07 +03:00
Eyrie
40166dbf08
Added job_id pattern for directories
2022-09-25 17:11:07 +03:00
AUTOMATIC
c82e32652e
prevent weird behavior when pressing interrupt just as image finishes
2022-09-23 08:48:19 +03:00
d8ahazard
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
2022-09-21 16:06:37 +03:00
C43H66N12O12S2
5f71ecfe6f
Update webui.py
2022-09-20 23:31:06 +03:00
C43H66N12O12S2
62ca23ac5b
add swinir import
2022-09-20 23:31:06 +03:00
C43H66N12O12S2
ae8e21abdd
hack
2022-09-20 23:31:06 +03:00
Connum
f3965cce01
added command line argument --autolaunch to open the webui URL in the system's default browser upon launch (implements #274 )
2022-09-18 22:39:34 +03:00
AUTOMATIC
247f58a5e7
add support for switching model checkpoints at runtime
2022-09-17 12:05:18 +03:00
AUTOMATIC
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
2022-09-12 20:47:46 +03:00
AUTOMATIC
834b6e396b
aaaaaaaaaaaaaaaaa
2022-09-12 16:52:06 +03:00
AUTOMATIC
89d94e13a7
rename --channelslast to --opt-channelslast to be in line with other torch optimizations
2022-09-12 16:51:23 +03:00
C43H66N12O12S2
fbeadef130
webui.py channels last support
2022-09-12 16:26:42 +03:00
AUTOMATIC
2938dc39fc
fixed gradio auth bug in PR
2022-09-12 15:52:16 +03:00
EyeDeck
fc49844aa8
Merge branch 'master' into master
2022-09-12 08:19:14 -04:00
AUTOMATIC
372a2c3e2e
[Feature Request] Please add "--share-password" for Gradio server security #315
2022-09-12 15:10:05 +03:00
EyeDeck
e3646e79aa
Add --auth command line argument to enable Gradio authentication
...
Allows you to pass in Gradio authentication like:
`--auth username:password`
Supports multiple sets of credentials by comma-delimiting, like:
`--auth user1:pass1,user2:pass3`...
2022-09-12 08:08:41 -04:00
AUTOMATIC
ddc86f2edb
--gradio-debug for collab users
2022-09-12 12:40:55 +03:00
AUTOMATIC
f194457229
CLIP interrogator
2022-09-11 18:48:36 +03:00
AUTOMATIC
f185874418
[Feature Request] Save defaults for extras & keep image parameters after using extras #251
2022-09-11 11:31:16 +03:00
AUTOMATIC
02bcd51a5a
fix aggressive caching for extras tab
2022-09-08 23:29:36 +03:00
AUTOMATIC
f5001246e2
honor tiling settings for RealESRGAN also
...
load scripts earlier to get errors before model loads
2022-09-08 15:19:36 +03:00
AUTOMATIC
3a4c6d9ef5
add webui() function for more simple cell in the notebook
2022-09-08 12:17:26 +03:00
orionaskatu
cce6f1df41
fix default
2022-09-08 10:46:23 +02:00
orionaskatu
48317a5176
Port defaults to none
2022-09-08 10:40:56 +02:00
orionaskatu
4f3cebd51d
Add server_port param to webui.py
2022-09-08 09:46:28 +02:00
AUTOMATIC
8dcd3e57e7
a little bit of rework for extras tab
2022-09-07 13:35:02 +03:00
AUTOMATIC
6a9b33c848
codeformer support
2022-09-07 12:32:28 +03:00
AUTOMATIC
7ce7fb01e0
fix for live progress breaking lowvram and medvram optimizations
2022-09-06 23:10:12 +03:00
AUTOMATIC
7e5b8becf9
fix for progress bar
2022-09-06 20:26:09 +03:00
AUTOMATIC
fd66199769
added preview option
2022-09-06 19:33:51 +03:00
AUTOMATIC
395f170597
readme extras for VRAM for
...
added missing packages to requirements for #74
add support for negative numbers in X/Y plot (plus ranges) #73
changed progressbar to work properly with custom modes
2022-09-06 10:11:25 +03:00
AUTOMATIC
beece7d85c
allow import as library for #72
2022-09-06 08:54:11 +03:00
AUTOMATIC
a243bc7859
added progressbar
...
added an option to disable progressbar
added interrupt support to DDIM/PLMS
2022-09-06 02:09:01 +03:00
AUTOMATIC
064965c466
added --listen option to make gradio listen on network requests
2022-09-05 19:37:11 +03:00
AUTOMATIC
a8a58dbac7
re-integrated tiling option as a UI element
2022-09-05 03:25:37 +03:00
AUTOMATIC
f91d0c3d19
add an option to enable tiling image generation
2022-09-05 02:16:36 +03:00
AUTOMATIC
f299645aee
ESRGAN support
2022-09-04 18:54:12 +03:00
hentailord85ez
e23a36b666
Fixed typo 'medram' -> 'medvram' in webui.py
2022-09-03 16:47:37 +01:00
AUTOMATIC
f40617d6c4
support for scripts
2022-09-03 17:21:15 +03:00
AUTOMATIC
345028099d
split codebase into multiple files; to anyone this affects negatively: sorry
2022-09-03 12:08:45 +03:00
AUTOMATIC
d7b67d9b40
load GFPGAN once and keep it in memory for #53
2022-09-03 09:05:48 +03:00
AUTOMATIC
0dca0db7eb
Update to support embedding with length greater than 1.
2022-09-03 01:01:58 +03:00
AUTOMATIC
4cafad66d2
this should send the currently selected image to other tabs instead of the first
2022-09-02 23:25:29 +03:00
AUTOMATIC
efa0a6483c
change webui.bat to use venv
2022-09-02 19:26:18 +03:00
AUTOMATIC
2000830342
Change SD upscales to save as images rather than grids and to respect image saving settings.
2022-09-02 15:33:01 +03:00
deggua
75fde6bcfe
Merge branch 'master' into automatic_master
2022-09-02 07:44:19 -04:00
deggua
4e2cc78e52
Removed unnecessary condition check for masking
2022-09-02 07:41:10 -04:00
AUTOMATIC
7ec7a3b121
fix for bad data in saved text files when batch size or batch cunt > 1
2022-09-02 14:33:43 +03:00
deggua
422981c85b
Forgot to remove the broken lines
2022-09-02 07:28:39 -04:00
deggua
f9c0046897
Fix for fill latent zeros/noise in masking mode
2022-09-02 07:18:12 -04:00
AUTOMATIC
38a483f976
buttons for sending images to tabs
2022-09-02 12:04:36 +03:00
AUTOMATIC
67216187a8
bat file for installing and launching
2022-09-02 09:49:35 +03:00
AUTOMATIC
8f7802f6d8
saving text files along with images for >>88400870
2022-09-02 02:12:50 +03:00
AUTOMATIC
6970696789
fix for torch 1.12.1 loading saved file from torch 1.11
2022-09-02 01:31:01 +03:00
AUTOMATIC
d5dfbc45a6
added detection if SD repo is located in a current directory
2022-09-02 01:06:11 +03:00
AUTOMATIC
b90feb02aa
option to disable ((())) and [[[]]]
2022-09-02 00:30:49 +03:00
AUTOMATIC
0a85f1afff
fix error messages not appearing
2022-09-02 00:24:30 +03:00
AUTOMATIC
47be7e1f1b
fix for #43
2022-09-01 23:52:29 +03:00
AUTOMATIC
63a3ae2b4c
fix images not displayed when not saving
...
fix lack of left padding for grids with 1 row
2022-09-01 22:38:25 +03:00
AUTOMATIC
5a6c0740ab
fix for broken extras tab
2022-09-01 22:17:59 +03:00
AUTOMATIC
0b8ca64aa2
applied workaround for gradio 3.2
2022-09-01 22:05:31 +03:00
AUTOMATIC
8d45b3be18
now things are going to work
2022-09-01 21:26:46 +03:00
AUTOMATIC
a6adc22f07
added interrupt button
...
added save button
--always-batch-cond-uncond as a workaround for performance regression option for low memory users
specify gradio version as 3.1.5 because of what looks like a bug
2022-09-01 21:20:25 +03:00
AUTOMATIC
54dc6f9307
actual support for share=True in gradio
2022-09-01 19:09:48 +03:00
AUTOMATIC
1940382f38
quick fix for a broken filename
2022-09-01 17:33:40 +03:00
AUTOMATIC
94e041fd2b
style changes related to the gradio update
2022-09-01 17:27:40 +03:00
AUTOMATIC
d28c94b8c3
output directory options
2022-09-01 17:11:47 +03:00
AUTOMATIC
2d5689a051
progress bar description for k-diffsuion for 88393097
2022-09-01 15:22:42 +03:00
AUTOMATIC
e1648fc1d1
changes for inpainting for #35
...
support for --medvram
attempt to support share
2022-09-01 11:41:42 +03:00
AUTOMATIC
3e4103541c
fix for PLMS not working
2022-08-31 23:40:11 +03:00
AUTOMATIC
757bb7c46b
fix for GPFGAN RGB/BGR (thanks deggua)
...
experimental support for negative prompts (without UI)
option to do inpainting at full resolution
Tooltips for UI elements
2022-08-31 22:19:30 +03:00
AUTOMATIC
a8c002587e
SD upscale parameters moved from options to the page
2022-08-31 17:32:26 +03:00
AUTOMATIC
51c65457c4
workaround for a weird bug in DDIM's make_schedule
2022-08-31 15:29:01 +03:00
AUTOMATIC
53e7616b51
DDIM support returned for img2img
2022-08-31 15:09:40 +03:00
AUTOMATIC
e38ad2ee95
added detailed installation instructions
...
fixed bug with missing same dir for a new install
added ctrl+c hander to immediately stop the program instead of waiting
2022-08-31 11:04:19 +03:00
orionaskatu
5ce4f66855
default value for txt2img samplers
2022-08-30 22:44:42 +02:00
AUTOMATIC
7434b3ebcc
updated interface to use Blocks
...
added mode toggle for img2img
added inpainting to readme
2022-08-30 21:51:30 +03:00
AUTOMATIC
bb2faa5fb8
applied fill to all but one inpainting modes, fixed issue with mask resizing
2022-08-30 14:39:26 +03:00
AUTOMATIC
ff98e09d72
UI options for mask blur and inpainting fill
2022-08-30 14:04:49 +03:00
AUTOMATIC
54f74d4472
added first version of inpainting
...
fixed flag option
2022-08-30 12:55:38 +03:00
AUTOMATIC
587db9c420
fixed some bugs in grid
...
changed some default values to more reasonable
added PNG info tab
2022-08-29 20:10:59 +03:00
AUTOMATIC
3402461055
gfpgan is not kept in memory
...
font selection setting
2022-08-29 16:42:00 +03:00
AUTOMATIC
808590654e
pushed the lost --precision switch fr anon to test i
2022-08-29 09:45:31 +03:00
AUTOMATIC
036a0dde70
forgot to remove debug messages
2022-08-29 02:17:41 +03:00
AUTOMATIC
9c9f048b5e
support for generating images on video cards with 4GB
2022-08-29 01:58:15 +03:00
AUTOMATIC
7a7a3a6b19
Option to not save grid for single images for #22
2022-08-28 21:11:58 +03:00
AUTOMATIC1111
6bec9c3a4f
Merge pull request #21 from orionaskatu/patch-1
...
Typo StableDiffuion
2022-08-28 21:01:50 +03:00
orionaskatu
20c33f4423
Queue concurrency 1 to prevent CUDA OOM
...
Mandatory for me as I have a RTX 2070 (8Gb) and I get CUDA OOM if two users launch jobs at the same time.
I can also use multiple tabs and jobs will be queued.
You may not want it to be the default though.
2022-08-28 16:12:55 +02:00
orionaskatu
e5480e3688
Typo StableDiffuion
...
Small typo StableDiffuionModelHijack() => StableDiffusionModelHijack()
2022-08-28 15:46:44 +02:00
