122d42687b
Fix VRAM Issue by only loading in hypernetwork when selected in settings
3 years ago
34acad1628
Add GZipMiddleware to root demo
3 years ago
786d9f63aa
Add button to skip the current iteration
3 years ago
12c4d5c6b5
hypernetwork training mk1
3 years ago
2a53280495
reorder imports to fix the bug with k-diffusion on some version
3 years ago
5f24b7bcf4
option to let users select which samplers they want to hide
3 years ago
c0389eb307
hello
3 years ago
688c4a914a
Merge branch 'master' into 1404-script-reload-without-restart
3 years ago
a634c3226f
correct indent
3 years ago
a1cde7e646
disabled SD model download after multiple complaints
3 years ago
5d26ba2b4b
Merge branch 'master' into ScuNET
3 years ago
820f1dc96b
initial support for training textual inversion
3 years ago
30f2e35658
add importlib.reload
3 years ago
a9044475c0
add time import
3 years ago
95f35d04ab
Host busy thread, check for reload
3 years ago
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.
3 years ago
d1f098540a
remove unwanted formatting/functionality from the PR
3 years ago
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
3 years ago
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.
3 years ago
2f2d356e4c
call torch_gc before/after each gpu gradio operation
3 years ago
5756d517a6
Merge remote-tracking branch 'upstream/master' into ModelLoader
3 years ago
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.
3 years ago
7d5c29b674
Cleanup existing directories, fixes
3 years ago
740070ea9c
Re-implement universal model loading
3 years ago
91643f651d
Add support for checkpoint merging
3 years ago
1877a3767e
Changed job_id to timestamp
3 years ago
40166dbf08
Added job_id pattern for directories
3 years ago
c82e32652e
prevent weird behavior when pressing interrupt just as image finishes
3 years ago
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
3 years ago
5f71ecfe6f
Update webui.py
3 years ago
62ca23ac5b
add swinir import
3 years ago
ae8e21abdd
hack
3 years ago
f3965cce01
added command line argument --autolaunch to open the webui URL in the system's default browser upon launch (implements #274 )
3 years ago
247f58a5e7
add support for switching model checkpoints at runtime
3 years ago
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
3 years ago
834b6e396b
aaaaaaaaaaaaaaaaa
3 years ago
89d94e13a7
rename --channelslast to --opt-channelslast to be in line with other torch optimizations
3 years ago
fbeadef130
webui.py channels last support
3 years ago
2938dc39fc
fixed gradio auth bug in PR
3 years ago
fc49844aa8
Merge branch 'master' into master
3 years ago
372a2c3e2e
[Feature Request] Please add "--share-password" for Gradio server security #315
3 years ago
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`...
3 years ago
ddc86f2edb
--gradio-debug for collab users
3 years ago
f194457229
CLIP interrogator
3 years ago
f185874418
[Feature Request] Save defaults for extras & keep image parameters after using extras #251
3 years ago
02bcd51a5a
fix aggressive caching for extras tab
3 years ago
f5001246e2
honor tiling settings for RealESRGAN also
...
load scripts earlier to get errors before model loads
3 years ago
3a4c6d9ef5
add webui() function for more simple cell in the notebook
3 years ago
cce6f1df41
fix default
3 years ago
48317a5176
Port defaults to none
3 years ago
4f3cebd51d
Add server_port param to webui.py
3 years ago
8dcd3e57e7
a little bit of rework for extras tab
3 years ago
6a9b33c848
codeformer support
3 years ago
7ce7fb01e0
fix for live progress breaking lowvram and medvram optimizations
3 years ago
7e5b8becf9
fix for progress bar
3 years ago
fd66199769
added preview option
3 years ago
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
3 years ago
beece7d85c
allow import as library for #72
3 years ago
a243bc7859
added progressbar
...
added an option to disable progressbar
added interrupt support to DDIM/PLMS
3 years ago
064965c466
added --listen option to make gradio listen on network requests
3 years ago
a8a58dbac7
re-integrated tiling option as a UI element
3 years ago
f91d0c3d19
add an option to enable tiling image generation
3 years ago
f299645aee
ESRGAN support
3 years ago
e23a36b666
Fixed typo 'medram' -> 'medvram' in webui.py
3 years ago
f40617d6c4
support for scripts
3 years ago
345028099d
split codebase into multiple files; to anyone this affects negatively: sorry
3 years ago
d7b67d9b40
load GFPGAN once and keep it in memory for #53
3 years ago
0dca0db7eb
Update to support embedding with length greater than 1.
3 years ago
4cafad66d2
this should send the currently selected image to other tabs instead of the first
3 years ago
efa0a6483c
change webui.bat to use venv
3 years ago
2000830342
Change SD upscales to save as images rather than grids and to respect image saving settings.
3 years ago
75fde6bcfe
Merge branch 'master' into automatic_master
3 years ago
4e2cc78e52
Removed unnecessary condition check for masking
3 years ago
7ec7a3b121
fix for bad data in saved text files when batch size or batch cunt > 1
3 years ago
422981c85b
Forgot to remove the broken lines
3 years ago
f9c0046897
Fix for fill latent zeros/noise in masking mode
3 years ago
38a483f976
buttons for sending images to tabs
3 years ago
67216187a8
bat file for installing and launching
3 years ago
8f7802f6d8
saving text files along with images for >>88400870
3 years ago
6970696789
fix for torch 1.12.1 loading saved file from torch 1.11
3 years ago
d5dfbc45a6
added detection if SD repo is located in a current directory
3 years ago
b90feb02aa
option to disable ((())) and [[[]]]
3 years ago
0a85f1afff
fix error messages not appearing
3 years ago
47be7e1f1b
fix for #43
3 years ago
63a3ae2b4c
fix images not displayed when not saving
...
fix lack of left padding for grids with 1 row
3 years ago
5a6c0740ab
fix for broken extras tab
3 years ago
0b8ca64aa2
applied workaround for gradio 3.2
3 years ago
8d45b3be18
now things are going to work
3 years ago
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
3 years ago
54dc6f9307
actual support for share=True in gradio
3 years ago
1940382f38
quick fix for a broken filename
3 years ago
94e041fd2b
style changes related to the gradio update
3 years ago
d28c94b8c3
output directory options
3 years ago
2d5689a051
progress bar description for k-diffsuion for 88393097
3 years ago
e1648fc1d1
changes for inpainting for #35
...
support for --medvram
attempt to support share
3 years ago
3e4103541c
fix for PLMS not working
3 years ago
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
3 years ago
a8c002587e
SD upscale parameters moved from options to the page
3 years ago
51c65457c4
workaround for a weird bug in DDIM's make_schedule
3 years ago
53e7616b51
DDIM support returned for img2img
3 years ago
Fampai
DepFA
Trung Ngo
AUTOMATIC
d8ahazard
William Moorehouse
Eyrie
C43H66N12O12S2
Connum
EyeDeck
orionaskatu
hentailord85ez
deggua