sd-webui/stable-diffusion-webui
1
1
Fork 0
mirror of https://github.com/sd-webui/stable-diffusion-webui.git synced 2024-12-14 14:52:31 +03:00
Code Issues Projects Releases Wiki Activity
600 Commits 22 Branches 0 Tags 64 MiB
0fc3e592f7
Commit Graph

600 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
unnamedplugins
0fc3e592f7 Merge branch 'dev' of github.com:unnamedplugins/stable-diffusion-webui into dev 2022-09-13 10:57:37 -04:00
unnamedplugins
0c0e80d909 Add mask restore feature to streamlit, prevent color correction from modifying initial image when mask_restore is turned on 2022-09-13 10:57:07 -04:00
hlky
92b3159909
half precision streamlit txt2vid 
`RuntimeError: expected scalar type Half but found Float` with both `torch_dtype=torch.float16` and `revision="fp16"`
 2022-09-13 13:26:36 +01:00
Ahmad Abdullah
84bb985134
Update README.md (#1075) 
fix typo
 2022-09-13 13:39:18 +03:00
Syahmi Azhar
93d53f9c32
fix: launcher batch file fix #920, fix #605 
- Allow reading environment.yaml file in either LF or CRLF
- Only update environment if environment.yaml changes
- Remove custom_conda_path to discourage changing source file
- Fix unable to launch webui due to frontend module missing (#605)
 2022-09-13 12:13:23 +03:00
ZeroCool
63407de224
Merge pull request #1073 from ZeroCool940711/dev 
Changed the loading of the model on the txt2vid tab so the half models are only loaded if the no_half option on the config file is set to False.
 2022-09-13 01:51:25 -07:00
ZeroCool
169f0d158e
Merge branch 'sd-webui:dev' into dev 2022-09-13 01:50:31 -07:00
ZeroCool940711
cbbf33d735 Changed the loading of the model on the txt2vid tab so the half models are only loaded if the no_half option on the config file is set to False. 2022-09-13 01:49:03 -07:00
ZeroCool
65d251a7b1
Merge pull request #1071 from ZeroCool940711/dev 
Fixed num_inference_steps not matching the value you set on the UI.
 2022-09-13 00:51:24 -07:00
ZeroCool940711
299cef698d Merge remote-tracking branch 'origin/dev' into dev 2022-09-13 00:49:31 -07:00
ZeroCool940711
67cb1116c8 Made it so the sampling_steps is added to num_inference_steps, otherwise it would not match the value you set for it on the slider. 2022-09-13 00:47:30 -07:00
ZeroCool
2f86782acf
Merge pull request #1070 from briansemrau/feature/img2img-masking-fixes 
img2img mask fixes and fix image2noise normalization
 2022-09-13 00:08:19 -07:00
ZeroCool
0480804499
Merge branch 'dev' into feature/img2img-masking-fixes 2022-09-13 00:06:34 -07:00
ZeroCool
ad72deb3c0
Merge pull request #1067 from unnamedplugins/dev 
Fix issue where loopback was using batch mode
 2022-09-13 00:00:14 -07:00
Brian Semrau
003f97d52a img2img mask fixes and fix image2noise normalization 2022-09-13 02:04:26 -04:00
Joshua Kimsey
9432efc549 Fixed Sidebar CSS for 4K displays 2022-09-13 04:31:00 +01:00
unnamedplugins
2af42fed51 Fix indentation error that prevents mask_restore from working unless ESRGAN is turned on 2022-09-12 23:01:59 -04:00
unnamedplugins
acc5f7591a Fix issue where loopback was using batch mode 2022-09-12 21:43:53 -04:00
Thomas Mello
c63fcb1502
fix: disable live prompt parsing 2022-09-13 00:42:53 +03:00
ZeroCool
744fd269ec
Merge pull request #1059 from ZeroCool940711/dev 
Commented some print statements that were used for debugging and forgot to remove previously.
 2022-09-12 12:03:49 -07:00
ZeroCool940711
f80a2f69ca Commented some print statements that were used for debugging and forgot to remove previously. 2022-09-12 12:01:16 -07:00
ZeroCool
25d18fb7fe
Merge pull request #1058 from ZeroCool940711/dev 
Multiple Improvements to the txt2vid tab and other misc stuff.
 2022-09-12 11:54:34 -07:00
ZeroCool940711
e4d3971db7 Merge remote-tracking branch 'origin/dev' into dev 2022-09-12 11:44:52 -07:00
ZeroCool940711
1117b5604a -Added the Update Image Preview option to be part of the current tab options under Preview Settings. 
- Added Dynamic Preview Frequency option for the txt2vid tab which tries to find the lowest value for update_preview_frequency at which we can update the preview image during generation while at the same time minimizing the impact it has in performance.
- Added option to save a video file on the outputs/txt2vid-samples folder after the generation is complete similar to how the save_grid option works on other tabs.
- Added a video preview which shows a video on the txt2vid tab when the generation is completed.
- Formated some lines of code to make it use less space and fit on the a single screen.
- Added a script called Settings.py to the script folder in which Settings for the Setting page will be placed. Empty for now.
 2022-09-12 11:44:00 -07:00
Thomas Mello
08bbbf7d6d
Merge pull request #1035 from raefu/negative-prompt-dev 
support negative prompts separated by ###
 2022-09-12 20:28:41 +03:00
ZeroCool940711
4bb6f9d92b Renamed the save_grid option for txt2vid on the config file to be save_video, this will be used to determine if the user wants to save a video at the end of the generation or not, similar to the save_grid that is used on txt2img and img2img but for video. 2022-09-12 08:11:52 -07:00
Thomas Mello
d2a004ff7f
Merge pull request #1056 from briansemrau/feature/credit-img2img-methods 
Add comments crediting code authors. (probably not enough, but better…
 2022-09-12 17:28:57 +03:00
Brian Semrau
224bbdf8d6 Add comments crediting code authors. (probably not enough, but better than none) 2022-09-12 10:26:01 -04:00
endomorphosis
372ac31c20
add Gradio API endpoint settings (#1055) 
* add Gradio API endpoint settings
 2022-09-12 14:27:24 +03:00
Matt Soucy
4f7ea60a2e
Use the webui script directories as PWD (#946) 2022-09-12 11:41:47 +03:00
ZeroCool
ba63fd7004
Merge pull request #1040 from briansemrau/feature/st-img2img-masking 
Add masking to streamlit img2img
 2022-09-12 00:24:59 -07:00
Brian Semrau
1089ec1162 add masking to streamlit img2img, find_noise_for_image, matched_noise 2022-09-12 03:02:43 -04:00
ZeroCool
a75ce47c3c
Merge pull request #1045 from ZeroCool940711/dev 
Fixed an error with the metadata not able to be saved because of the …
 2022-09-12 00:00:18 -07:00
ZeroCool940711
9c8ac62b3d Fixed an error with the metadata not able to be saved because of the seed was not converted to a string before so it had no attribute encode on it. 2022-09-11 23:57:29 -07:00
ZeroCool
ec1f2b7e7d
Merge pull request #1043 from ZeroCool940711/dev 
Changes made by @Hafiidz to improve the appearance of the sidebar.
 2022-09-11 23:21:29 -07:00
ZeroCool940711
36a1551465 - Added code for @Hafiidz's changes made on the css. 2022-09-11 23:11:42 -07:00
ZeroCool940711
117046ccdc Removed the padding at the top of the sidebar so we can have more free space. 2022-09-11 22:50:43 -07:00
ZeroCool940711
a3ae2d4a94 Changed the cmd script to use the dark theme by default when launching the streamlit UI. 2022-09-11 22:49:39 -07:00
ZeroCool940711
dee13a11c6 Changed some values to be dynamic instead of a fixed value so they are more responsive. 2022-09-11 22:23:59 -07:00
ZeroCool940711
cbc2a57bc1 Added streamlit-on-Hover-tabs and streamlit-option-menu dependencies to the environment.yaml file. 2022-09-11 20:15:07 -07:00
ZeroCool940711
6e012fcc19 - Added changes made by @Hafiidz on the ui-improvements branch to the css for the streamli-on-hover-tabs component. 2022-09-11 20:11:35 -07:00
oc013
fa6ccf230c
Docker validate model files if not a symlink in case user has VALIDATE_MODELS=false set (#1038) 2022-09-12 01:30:50 +03:00
Rae Fu
2124b7208f support negative prompts separated by ### 
e.g. "shopping mall ### people" will try to generate an image of a mall
without people in it.
 2022-09-11 14:51:20 -06:00
M
9f8a7a61ad
webui: add prompt output to console (#1031) 
* webui: add prompt output to console

show the user what prompt is currently being rendered

* fix prompt print location
 2022-09-11 22:21:38 +03:00
ZeroCool
c3d12d9b14
Merge pull request #1029 from ZeroCool940711/dev 
Multiple improvements to the txt2vid tab
 2022-09-11 10:43:56 -07:00
ZeroCool
cf924ca11f
Merge branch 'sd-webui:dev' into dev 2022-09-11 10:43:01 -07:00
ZeroCool940711
20172d381e Multiple improvements to the txt2vid tab. 
- Improved txt2vid speed by 2 times.
- Added DDIM scheduler.
- Added sliders for beta_start and beta_end to have more control over these parameters on the scheduler.
- Added option to select the scheduler type from scaled_linear or linear.
- Added option to save info files for the txt2vid tab and improved the information saved to include most of the parameters used to run the generation.
- You can now download any model from the huggingface website to use on the txt2vid tab, just add the name to the custom_models_list on the config file.
 2022-09-11 10:42:17 -07:00
oc013
8a8b993fd5
Add missing comma for nsfw toggle in img2img (#1028) 2022-09-11 20:18:17 +03:00
Thomas Mello
9cdaee0cc9
Merge pull request #1027 from oc013/dev 
Docker - Set PYTHONPATH to parent directory to avoid `No module named frontend` error
 2022-09-11 20:16:11 +03:00
oc013
671b56f62f
Docker - Set PYTHONPATH to parent directory to avoid No module named frontend error 2022-09-11 12:36:28 -04:00