d1f098540a
remove unwanted formatting/functionality from the PR
2022-09-30 11:42:40 +03:00
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-29 19:59:36 -05:00
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
2f2d356e4c
call torch_gc before/after each gpu gradio operation
2022-09-29 11:32:12 +03:00
5756d517a6
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-27 11:02:41 -05:00
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
7d5c29b674
Cleanup existing directories, fixes
2022-09-26 10:27:18 -05:00
740070ea9c
Re-implement universal model loading
2022-09-26 09:29:50 -05:00
91643f651d
Add support for checkpoint merging
2022-09-25 19:22:12 -04:00
1877a3767e
Changed job_id to timestamp
2022-09-25 17:11:07 +03:00
40166dbf08
Added job_id pattern for directories
2022-09-25 17:11:07 +03:00
c82e32652e
prevent weird behavior when pressing interrupt just as image finishes
2022-09-23 08:48:19 +03:00
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
2022-09-21 16:06:37 +03:00
5f71ecfe6f
Update webui.py
2022-09-20 23:31:06 +03:00
62ca23ac5b
add swinir import
2022-09-20 23:31:06 +03:00
ae8e21abdd
hack
2022-09-20 23:31:06 +03:00
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
247f58a5e7
add support for switching model checkpoints at runtime
2022-09-17 12:05:18 +03:00
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
2022-09-12 20:47:46 +03:00
834b6e396b
aaaaaaaaaaaaaaaaa
2022-09-12 16:52:06 +03:00
89d94e13a7
rename --channelslast to --opt-channelslast to be in line with other torch optimizations
2022-09-12 16:51:23 +03:00
fbeadef130
webui.py channels last support
2022-09-12 16:26:42 +03:00
2938dc39fc
fixed gradio auth bug in PR
2022-09-12 15:52:16 +03:00
fc49844aa8
Merge branch 'master' into master
2022-09-12 08:19:14 -04:00
372a2c3e2e
[Feature Request] Please add "--share-password" for Gradio server security #315
2022-09-12 15:10:05 +03:00
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
ddc86f2edb
--gradio-debug for collab users
2022-09-12 12:40:55 +03:00
f194457229
CLIP interrogator
2022-09-11 18:48:36 +03:00
f185874418
[Feature Request] Save defaults for extras & keep image parameters after using extras #251
2022-09-11 11:31:16 +03:00
02bcd51a5a
fix aggressive caching for extras tab
2022-09-08 23:29:36 +03:00
f5001246e2
honor tiling settings for RealESRGAN also
...
load scripts earlier to get errors before model loads
2022-09-08 15:19:36 +03:00
3a4c6d9ef5
add webui() function for more simple cell in the notebook
2022-09-08 12:17:26 +03:00
cce6f1df41
fix default
2022-09-08 10:46:23 +02:00
48317a5176
Port defaults to none
2022-09-08 10:40:56 +02:00
4f3cebd51d
Add server_port param to webui.py
2022-09-08 09:46:28 +02:00
8dcd3e57e7
a little bit of rework for extras tab
2022-09-07 13:35:02 +03:00
6a9b33c848
codeformer support
2022-09-07 12:32:28 +03:00
7ce7fb01e0
fix for live progress breaking lowvram and medvram optimizations
2022-09-06 23:10:12 +03:00
7e5b8becf9
fix for progress bar
2022-09-06 20:26:09 +03:00
fd66199769
added preview option
2022-09-06 19:33:51 +03:00
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
beece7d85c
allow import as library for #72
2022-09-06 08:54:11 +03:00
a243bc7859
added progressbar
...
added an option to disable progressbar
added interrupt support to DDIM/PLMS
2022-09-06 02:09:01 +03:00
064965c466
added --listen option to make gradio listen on network requests
2022-09-05 19:37:11 +03:00
a8a58dbac7
re-integrated tiling option as a UI element
2022-09-05 03:25:37 +03:00
f91d0c3d19
add an option to enable tiling image generation
2022-09-05 02:16:36 +03:00
f299645aee
ESRGAN support
2022-09-04 18:54:12 +03:00
e23a36b666
Fixed typo 'medram' -> 'medvram' in webui.py
2022-09-03 16:47:37 +01:00
f40617d6c4
support for scripts
2022-09-03 17:21:15 +03:00
345028099d
split codebase into multiple files; to anyone this affects negatively: sorry
2022-09-03 12:08:45 +03:00
d7b67d9b40
load GFPGAN once and keep it in memory for #53
2022-09-03 09:05:48 +03:00
0dca0db7eb
Update to support embedding with length greater than 1.
2022-09-03 01:01:58 +03:00
4cafad66d2
this should send the currently selected image to other tabs instead of the first
2022-09-02 23:25:29 +03:00
efa0a6483c
change webui.bat to use venv
2022-09-02 19:26:18 +03:00
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
75fde6bcfe
Merge branch 'master' into automatic_master
2022-09-02 07:44:19 -04:00
4e2cc78e52
Removed unnecessary condition check for masking
2022-09-02 07:41:10 -04:00
7ec7a3b121
fix for bad data in saved text files when batch size or batch cunt > 1
2022-09-02 14:33:43 +03:00
422981c85b
Forgot to remove the broken lines
2022-09-02 07:28:39 -04:00
f9c0046897
Fix for fill latent zeros/noise in masking mode
2022-09-02 07:18:12 -04:00
38a483f976
buttons for sending images to tabs
2022-09-02 12:04:36 +03:00
67216187a8
bat file for installing and launching
2022-09-02 09:49:35 +03:00
8f7802f6d8
saving text files along with images for >>88400870
2022-09-02 02:12:50 +03:00
6970696789
fix for torch 1.12.1 loading saved file from torch 1.11
2022-09-02 01:31:01 +03:00
d5dfbc45a6
added detection if SD repo is located in a current directory
2022-09-02 01:06:11 +03:00
b90feb02aa
option to disable ((())) and [[[]]]
2022-09-02 00:30:49 +03:00
0a85f1afff
fix error messages not appearing
2022-09-02 00:24:30 +03:00
47be7e1f1b
fix for #43
2022-09-01 23:52:29 +03:00
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
5a6c0740ab
fix for broken extras tab
2022-09-01 22:17:59 +03:00
0b8ca64aa2
applied workaround for gradio 3.2
2022-09-01 22:05:31 +03:00
8d45b3be18
now things are going to work
2022-09-01 21:26:46 +03:00
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
54dc6f9307
actual support for share=True in gradio
2022-09-01 19:09:48 +03:00
1940382f38
quick fix for a broken filename
2022-09-01 17:33:40 +03:00
94e041fd2b
style changes related to the gradio update
2022-09-01 17:27:40 +03:00
d28c94b8c3
output directory options
2022-09-01 17:11:47 +03:00
2d5689a051
progress bar description for k-diffsuion for 88393097
2022-09-01 15:22:42 +03:00
e1648fc1d1
changes for inpainting for #35
...
support for --medvram
attempt to support share
2022-09-01 11:41:42 +03:00
3e4103541c
fix for PLMS not working
2022-08-31 23:40:11 +03:00
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
a8c002587e
SD upscale parameters moved from options to the page
2022-08-31 17:32:26 +03:00
51c65457c4
workaround for a weird bug in DDIM's make_schedule
2022-08-31 15:29:01 +03:00
53e7616b51
DDIM support returned for img2img
2022-08-31 15:09:40 +03:00
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
5ce4f66855
default value for txt2img samplers
2022-08-30 22:44:42 +02:00
7434b3ebcc
updated interface to use Blocks
...
added mode toggle for img2img
added inpainting to readme
2022-08-30 21:51:30 +03:00
bb2faa5fb8
applied fill to all but one inpainting modes, fixed issue with mask resizing
2022-08-30 14:39:26 +03:00
ff98e09d72
UI options for mask blur and inpainting fill
2022-08-30 14:04:49 +03:00
54f74d4472
added first version of inpainting
...
fixed flag option
2022-08-30 12:55:38 +03:00
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
3402461055
gfpgan is not kept in memory
...
font selection setting
2022-08-29 16:42:00 +03:00
808590654e
pushed the lost --precision switch fr anon to test i
2022-08-29 09:45:31 +03:00
036a0dde70
forgot to remove debug messages
2022-08-29 02:17:41 +03:00
9c9f048b5e
support for generating images on video cards with 4GB
2022-08-29 01:58:15 +03:00
7a7a3a6b19
Option to not save grid for single images for #22
2022-08-28 21:11:58 +03:00
6bec9c3a4f
Merge pull request #21 from orionaskatu/patch-1
...
Typo StableDiffuion
2022-08-28 21:01:50 +03:00
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
e5480e3688
Typo StableDiffuion
...
Small typo StableDiffuionModelHijack() => StableDiffusionModelHijack()
2022-08-28 15:46:44 +02:00
93e7dbaa71
support for running custom code (primarily to generate various labeled grids)
...
export for 4chan option
2022-08-28 16:38:59 +03:00
d5266c07f9
split draw_prompt_matrix into two: generalized grid annotation and actual prompt matrix
...
disabled saving samples for SD upscale
2022-08-28 09:27:07 +03:00
4ed435dd85
add upscaler modes for #19
2022-08-28 07:49:37 +03:00
c30aee2f4b
fixed all lines PyCharm was nagging me about
...
fixed input verification not working properly with long textual inversion tokens in some cases (plus it will prevent incorrect outputs for forks that use the :::: prompt weighing method)
changed process_images to object class with same fields as args it was previously accepting
changed options system to make it possible to explicitly specify gradio objects with args
2022-08-27 21:32:28 +03:00
4e0fdca2f4
Implementation for SD upscale.
2022-08-27 16:13:33 +03:00
9597b265ec
implementation for attention using [] and ()
2022-08-27 11:17:55 +03:00
92138df5cc
fix gfpgan oom on 6GB
...
force a gc if out of memory
2022-08-26 11:56:04 -05:00
21bcbb945e
fix a bug with wrong row count in prompt matrix
2022-08-26 18:04:00 +03:00
21765c17e6
added samples to img2img
...
fixed a bug with sampler selection (oops)
2022-08-26 14:10:40 +03:00
155dd2fc0c
Renamed GFPGAN to extras
...
Added Real-ESRGAN to extras tab
2022-08-26 11:16:57 +03:00
055dd10aae
Add Denoising Strength to output parameters in the output text
2022-08-26 09:02:21 +03:00
5e83e7081a
option to add prompt matrix variable text parts to start of the prompt rather than the end
2022-08-26 08:47:44 +03:00
c9579b51a6
extra samplers from K-diffusion
2022-08-25 23:31:44 +03:00
91dc8710ec
textual inversion embeddings support
...
settings tab
2022-08-25 21:52:05 +03:00
6a8e76e37f
Check for the embedding manager
2022-08-24 21:46:50 +03:00
781f054a20
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
2022-08-24 21:38:14 +03:00
4b0188dcbf
Textual inversion support
2022-08-24 21:20:36 +03:00
199123e98d
add execution timings to output
...
change the text output element to HTML
2022-08-24 18:47:23 +03:00
29f7e7ab89
save image generation params into text chunks for png images
2022-08-24 17:57:49 +03:00
da96bbf485
commandline options to control saved file type/quality/names
2022-08-24 17:41:37 +03:00
15a700bbe5
Merge branch 'master' into master
2022-08-24 16:50:57 +03:00
32dd552883
loopback mode for img2img
...
commandline options for grid filetypes and max batch count
2022-08-24 16:42:22 +03:00
abb83239e5
torch_gc/empty cache after generation
...
added torch_gc() which calls both cuda.empty_cache() and cuda.ipc_collect()
called before and after generation
2022-08-24 14:12:33 +01:00
29d0d65504
jpg grid, named grid
...
Grid file named with seed and prompt, output as jpg
2022-08-24 12:44:48 +01:00
852baf422a
gfpgan dir for the guide's directory names
...
fix a bug in image resizing
2022-08-24 13:42:21 +03:00
1463d44faf
added resizing modes
...
added more info into readme
2022-08-24 10:52:41 +03:00
2a0f8afb29
remove remote image as sample for img2img (it will now use a local image if you have one, none otherwise)
2022-08-24 09:24:32 +03:00
6efddcb279
hide gradio progressbar for about 10% speed increase on my GPU; a commandline option to prevent hiding
2022-08-24 09:06:36 +03:00
165da39fb1
fixed a possible issue with older versions of PIL
2022-08-24 01:08:59 +03:00
81087207bc
--no-half commandline option to disable .half()
2022-08-24 00:38:53 +03:00
7fd0f31661
added prompt verification: if it's too long, a warning is returned in the text field along with the part of prompt that has been truncated
2022-08-24 00:02:43 +03:00
aa67540eba
Added prompt matrix to img2img
...
refactoring: separated duplicate code from img2img and txt2img into a single function
2022-08-23 22:42:43 +03:00
cb118c4036
Prompt matrix now draws text like in demo.
2022-08-23 18:04:13 +03:00
61bfa6c16b
additional picture for prompt matrix
...
proper seeds for img2img
a bit of refactoring
2022-08-23 14:07:37 +03:00
60e95f1d8c
silence the warning from transformers
...
add feature demonstrations to readme
2022-08-23 11:58:50 +03:00
3395c29127
added prompt matrix feature
...
all images in batches now have proper seeds, not just the first one
added code to remove bad characters from filenames
added code to flag output which writes it to csv and saves images
renamed some fields in UI for clarity
2022-08-23 00:34:49 +03:00
b63d0726cd
fixed bug with images not resizing for img2img
...
added GFPGAN as an option for img2img
added GFPGAN as a tab
added autodetection for row counts for grids, enabled by default
removed Fixed Code sampling because no one can figure out what it does; maybe someone will be upset by removal and will tell me
2022-08-22 20:08:32 +03:00
3324f31e84
first
2022-08-22 17:15:46 +03:00
AUTOMATIC