Commit Graph

632 Commits

Author SHA1 Message Date
ZeroCool
be2ece0683
Merge pull request #959 from jjisnow/new_metadata
New metadata for other image types
2022-09-10 19:11:32 -07:00
ZeroCool
c3cde0b661
Merge pull request #990 from jjisnow/img2img-defaults
add sampler_name defaults to img2img
2022-09-10 19:10:10 -07:00
Thomas Mello
8191be5e0d
Merge pull request #995 from Hafiidz/dev-source-warning
remove deprecated kwargs/parameter
2022-09-11 04:42:51 +03:00
M
20adc46b75
webui: detect scoped-down GPU environment (#993)
* webui: detect scoped-down GPU environment

check if we're using a scoped-down GPU environment (pynvml does not listen to CUDA_VISIBLE_DEVICES) so that we can measure memory on the correct GPU

* remove unnecessary import
2022-09-11 04:41:29 +03:00
Thomas Mello
8039021b53 refactor: sort out dependencies
Co-Authored-By: oc013 <101832295+oc013@users.noreply.github.com>
Co-Authored-By: Aarni Koskela <akx@iki.fi>
Co-Authored-By: oc013 <101832295+oc013@users.noreply.github.com>
Co-Authored-By: Aarni Koskela <akx@iki.fi>
2022-09-11 04:33:43 +03:00
Hafiidz
0a3d4eea58 remove deprecated kwargs/parameter 2022-09-11 09:21:32 +08:00
JJ
8e7959ca2b add metadata to other file output file types 2022-09-11 09:49:14 +10:00
JJ
b4db9733d0 add sampler_name defaults to img2img 2022-09-11 09:37:14 +10:00
Thomas Mello
d6f4796c35
fix: sampler name in GoBig #988 2022-09-11 01:52:51 +03:00
xaedes
008af2d8ff
Perform masked image restoration for GFPGAN, RealESRGAN, fixing #947
* Perform masked image restoration when using GFPGAN or RealESRGAN, fixing #947.
Also fixes bug in image display when using masked image restoration with RealESRGAN.

When the image is upscaled using RealESRGAN the image restoration can not use the
original image because it has wrong resolution. In this case the image restoration
will restore the non-regenerated parts of the image with an RealESRGAN upscaled
version of the original input image.

Modifications from GFPGAN or color correction in (un)masked parts are also restored
to the original image by mask blending.

* Update scripts/webui.py

Co-authored-by: Thomas Mello <work.mello@gmail.com>
2022-09-10 18:37:42 +03:00
ZeroCool
f39b71a107
Merge pull request #968 from ZeroCool940711/dev
Improved the progress bar for the txt2vid tab and other fixes.
2022-09-10 07:43:56 -07:00
ZeroCool
24ddbdc811
Merge branch 'sd-webui:dev' into dev 2022-09-10 07:42:59 -07:00
ZeroCool940711
80b00810ef - Improved the progress bar for the txt2vid tab, it now shows more information during generation.
- Changed the guidance_scale variable to be cfg_scale.
2022-09-10 07:42:20 -07:00
ZeroCool940711
527d18e1c6 Added two new scripts that will be used for the new implementation of the txt2vid tab which uses the latest version of the diffusers library. 2022-09-10 07:38:57 -07:00
ZeroCool940711
9c7f401310 Added the models/custom folder to gitignore to ignore custom models. 2022-09-10 07:38:02 -07:00
ZeroCool940711
c7894b090a Changed the diffusers version to be 0.2.4 or lower as a new version breaks the txt2vid generation. 2022-09-10 07:37:28 -07:00
ZeroCool940711
a4745cc2fc Removed some unused lines from the css file for the streamlit version. 2022-09-10 07:34:35 -07:00
Soul-Burn
3e9cdb1dcb Better support for large batches in optimized mode 2022-09-10 15:25:13 +01:00
ZeroCool
53aacef732
Merge pull request #954 from ZeroCool940711/dev
Changed the scheduler for the txt2vid tab back to LMS.
2022-09-09 19:52:38 -07:00
ZeroCool
1a2106c6b3
Merge branch 'sd-webui:dev' into dev 2022-09-09 19:52:01 -07:00
ZeroCool940711
8bc59c48df Merge remote-tracking branch 'origin/dev' into dev 2022-09-09 19:51:35 -07:00
ZeroCool940711
2795dfb8ab Changed the scheduler for the txt2vid tab back to LMS, for now we can only use that. 2022-09-09 19:51:28 -07:00
ZeroCool940711
f5df32efb7 Removed old files from a split test we deed that are not needed anymore, we plan to do the split differently. 2022-09-09 19:47:43 -07:00
ZeroCool
93b6021d38
Merge pull request #953 from ZeroCool940711/dev
Fixed an issue with the txt2vid model.
2022-09-09 19:45:07 -07:00
ZeroCool
b4dd35ac08
Merge branch 'sd-webui:dev' into dev 2022-09-09 19:44:21 -07:00
ZeroCool940711
249e2dd74f Fixed an issue with the txt2vid model. 2022-09-09 19:43:51 -07:00
ZeroCool
4d2b0be3b5
Merge pull request #951 from JoshuaKimsey/fix-yaml-defaults
Changed StreamIit default sampler to `k_euler` and 30 steps.
2022-09-09 19:42:52 -07:00
Joshua Kimsey
05ff68c539 Changed StreamIt to k_euler 30 steps as default 2022-09-09 22:39:33 -04:00
ZeroCool
ec38e45fd7
Merge pull request #873 from JoshuaKimsey/fix-streamit-yaml
Changed Streamit yaml default configs
2022-09-09 17:54:59 -07:00
Thomas Mello
f8a6a4eba8
fix: lost imports from #921 2022-09-10 01:54:19 +03:00
Thomas Mello
de0bf059e9
Merge pull request #921 from mike-hearn/master
Image transparency can be used as mask for inpainting
2022-09-10 01:32:47 +03:00
Michael Hearn
002dca063d Image transparency is used as mask for inpainting 2022-09-09 18:28:40 -04:00
xaedes
07062941c7
add img2img option for color correction. (#936)
color correction is already used for loopback to prevent color drift with the first image as correction target.
the option allows to use the color correction even without loopback mode.
it helps keeping the colors similar to the input image.
2022-09-10 00:44:30 +03:00
James Pound
32a3c05af7 Added CSS to center the image in the txt2img interface 2022-09-09 22:36:53 +01:00
xaedes
f6aa2c64eb
Add mask_restore to restore images based on mask, fixing #665 (#898)
* Add mask_restore option to give users the option to restore images based on mask, fixing #665.

Before commit c73fdd78  (Implement masking during sampling to improve blending, #308)
image mask was applied after sampling, resulting in masked parts that are not regenerated
to actually stay the same.
Since c73fdd78 the masked img2img will change the whole image, even in masked areas.
It gives better looking results at first glance, but will result in image degredation when
applied a few times. See issue #665.

In the workflow of using repeated masked img2img, users may want to use this options to keep the parts
of image they actually want to keep without image degradation. A final masked img2img or whole image img2img with mask_restore disabled
will give the better blending of "Implement masking during sampling".

* revert changes of a7be43ba in change_image_editor_mode

* fix ui_functions.change_image_editor_mode by adding gr.update to the end of the list it returns

* revert inserted newlines and whitespaces to match format of previous code

* improve caption of new option mask_restore

"Only modify regenerated parts of image"

* fix ui_functions.change_image_editor_mode by adding gr.update to the end of the list it returns

an old copy of the function exists in webui.py, this superflous function mistakenly was changed by the earlier commit b6a9e16b

* remove unused functions that are near duplicates of functions in ui_functions.py
2022-09-10 00:07:14 +03:00
hlky
d054ebe60c
Remove embeddings file path 2022-09-09 22:03:20 +01:00
Hafiidz
c7d6855bae For issue :884, ensure webui.cmd before init src 2022-09-09 21:54:30 +01:00
Thomas Mello
16d2941619
fix: filename format parameter (#923) 2022-09-09 22:11:57 +03:00
VulumeCode
1422b35ac6
Tiling parameter (#911)
* tiling

* default to False
2022-09-09 20:33:04 +03:00
Michoko
4d76d6742c
Add filename formatting argument (#908)
* Update webui.py

Filename formatting argument

* Update scripts/webui.py

Co-authored-by: Thomas Mello <work.mello@gmail.com>
2022-09-09 20:20:59 +03:00
cobryan05
9d95449624
Metadata cleanup - Maintain metadata within UI (#845)
* Metadata cleanup - Maintain metadata within UI

This commit, when combined with Gradio 3.2.1b1+, maintains image
metadata as an image is passed throughout the UI. For example,
if you generate an image, send it to Image Lab, upscale it, fix faces,
and then drag the resulting image back in to Image Lab, it will still
remember the image generation parameters.

When the image is saved, the metadata will be stripped from it if
save-metadata is not enabled. If the image is saved by *dragging*
out of the UI on to the filesystem it may maintain its metadata.

Note: I have ran into UI responsiveness issues with upgrading Gradio.
Seems there may be some Gradio queue management issues. *Without* the
gradio update this commit will maintain current functionality, but
will not keep meetadata when dragging an image between UI components.

* Move ImageMetadata into its own file

Cleans up webui, enables webui_streamlit et al to use it as well.

* Fix typo
2022-09-09 19:27:21 +03:00
James Pound
c37de9f04e
Fixed aspect ratio box not being updated on txt2img tab, for issue 219 from old repo (#812) 2022-09-09 17:58:59 +03:00
Thomas Mello
da9dab22a7
Merge pull request #872 from nagolinc/voroni-outcrop
Improve outpainting with Perlin noise
2022-09-09 17:39:12 +03:00
M
70db27fa6a
frontend: display current device info (#889)
Displays the current device info at the bottom of the page.

For users who run multiple instances of `sd-webui` on the same system (for multiple GPUs), it helps to know which of the active `CUDA_VISIBLE_DEVICES` is being used.
2022-09-09 17:16:39 +03:00
Logan zoellner
754e530d70 when in outcrop mode, mask added regions and fill in with voroni noise for better outpainting 2022-09-09 10:13:38 -04:00
hlky
8d5977e15b Update FUNDING.yml 2022-09-09 10:13:38 -04:00
TingTingin
c459bfaacc Update attention.py 2022-09-09 14:21:53 +01:00
ZeroCool
90a922c320
Merge pull request #895 from Hafiidz/dev
Urgent Fix to PR:860
2022-09-09 04:29:44 -07:00
Hafiidz
11af1d9338 Urgent Fix to PR:860 2022-09-09 19:07:35 +08:00
ZeroCool
bd0e3655c1
Merge pull request #893 from ZeroCool940711/dev
Improvements to the txt2vid tab.
2022-09-09 03:45:22 -07:00