Commit Graph

1278 Commits

Author SHA1 Message Date
ZeroCool940711
2a078d5657 Fixed missing keys on first run, it seems related to server_state doing a rerun in the background on first run which changes the first session_state initialization, this causes it to be empty until the second run. 2022-10-02 21:50:24 -07:00
Alejandro Gil
e975aac7a4
Fixed multiple settings and default values not working properly. (#1403) 2022-10-02 21:26:26 -07:00
Alejandro Gil
891c4be726
Merge branch 'sd-webui:dev' into dev 2022-10-02 21:26:01 -07:00
ZeroCool940711
f866ffdad4 Fixed multiple settings and default values not working properly. 2022-10-02 21:25:41 -07:00
Alejandro Gil
f230e32010
Fixed LDSR, now it should work both txt2img and img2img (#1402)
- Removed slider values for batch_count and batch_size as they are now a
text_input instead of a slider.
- Removed the checkbox to disable the preview image, instead users
should increase the frequency at which it is displayed if they have
performance issues, after a certain point it no longer affects
performance.
- Removed GFPGAN GitHub dependency, we can now use pip to install a
fixed version of it.
- Fixed LDSR, now it should work both txt2img and img2img
2022-10-02 20:28:31 -07:00
ZeroCool940711
393a695aef Fixed LDSR, now it should work both txt2img and img2img 2022-10-02 20:26:01 -07:00
ZeroCool940711
8239c328fd Merge remote-tracking branch 'origin/dev' into dev 2022-10-02 16:27:43 -07:00
Travis Fletcher
a06c4081d9
Add missing GPFGANv1.4 model to docker list (#1394)
# Description
Add GFPGANv1.4 to the docker download list

Closes: none

# Checklist:

- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
2022-10-02 22:15:38 +01:00
lukas5450
14c5502b13
fixed missing 'GFPGANv1.4 in doc (#1397)
# Description

Please include:
* relevant motivation
* a summary of the change
* which issue is fixed.
* any additional dependencies that are required for this change.

Closes: #1395 

# Checklist:

- [ ] I have changed the base branch to `dev`
- [ ] I have performed a self-review of my own code
- [ ] I have commented my code in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
2022-10-02 22:15:14 +01:00
xaedes
1b6f6e5652
Add Scene2Image documentation (#1399)
# Description

Add section for Scene2Image in markdown documentation.

# Checklist:

- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation

Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
2022-10-02 22:14:52 +01:00
ZeroCool940711
f5254de10a Merge remote-tracking branch 'origin/dev' into dev 2022-10-02 13:43:37 -07:00
hlky
0050d54a1a default=false 2022-10-02 21:20:46 +01:00
hlky
3e75fe404b
default=false 2022-10-02 21:19:50 +01:00
ZeroCool940711
0f648e808a Merge remote-tracking branch 'origin/dev' into dev 2022-10-02 13:14:16 -07:00
ZeroCool940711
d47c258eaa Removed GFPGAN github dependency, we can now use pip to install a fixed version of it. 2022-10-02 13:11:30 -07:00
ZeroCool940711
7354c901d2 Fixed LDSR not working on txt2img and img2img.
- Removed the checkbox to disable the preview image, instead users should increase the frequency at which it is displayed if they have performance issues, after a certain point it no longer affects performance.
2022-10-02 13:10:17 -07:00
ZeroCool940711
38ff4a138c Removed slider values for batch_count and batch_size as they are now a text_input instead of a slider. 2022-10-02 13:08:37 -07:00
xaedes
a88cf2a22c
Add metadata to scn2img intermediate image output (#1386)
# Description

Intermediate image saving in scn2img tries to save metadata which is not
set. This results in warning thrown in console: "Couldn't find metadata
on image", originally reported by @codedealer in
https://github.com/sd-webui/stable-diffusion-webui/pull/1179#pullrequestreview-1120015859

Metadata for intermediate images is added to fix the warning.

Following metadata is written:
- "prompt" contains the representation of the SceneObject corresponding
to the intermediate image
- "seed" contains the seed at the start of the function that generated
this intermediate image
- "width" and "height" contain the size of the image.

To get the seed at the start of the render function without using it, a
class SeedGenerator is added and used instead of the python generator
functions.

Fixes warning thrown in console: "> Couldn't find metadata on image",
originally reported by @codedealer in
https://github.com/sd-webui/stable-diffusion-webui/pull/1179#pullrequestreview-1120015859

# Checklist:

- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
2022-10-02 20:56:49 +01:00
hlky
81b41ce0d3
The Merge (#1387) 2022-10-02 19:48:30 +01:00
hlky
f3d5068951
Revert "Merge branch 'master' into dev"
This reverts commit 73e513ae5a, reversing
changes made to bb8850b9dd.
2022-10-02 19:42:07 +01:00
hlky
73e513ae5a
Merge branch 'master' into dev 2022-10-02 19:41:40 +01:00
Divided by Zer0
bb8850b9dd
Allows passing args to webui.sh and webui.cmd (#1385)
This change helps with starting the stable horde bridge, without having
to change the relauncher.py every time. It also allows one to start
multiple bridges (for multiple GPUs) by passing the `-n` argument to the
.cmd/.sh
2022-10-02 19:24:23 +01:00
Alejandro Gil
481c4d83cd
Updated the model manager with the new locations and models links. (#1384) 2022-10-02 11:00:50 -07:00
Alejandro Gil
fdf600b49a
Merge branch 'sd-webui:dev' into dev 2022-10-02 11:00:24 -07:00
ZeroCool940711
e950720f9e Updated the model manager with the new locations and models links. 2022-10-02 10:59:20 -07:00
xaedes
33b896d0cb
Scene-to-Image Prompt Layering System (#1179)
# Summary of the change

- new Scene-to-Image tab
- new scn2img function
- functions for loading and running monocular_depth_estimation with
tensorflow

# Description

(relevant motivation, which issue is fixed)

Related to discussion #925

> Would it be possible to have a layers system where we could do have
foreground, mid, and background objects which relate to one another and
share the style? So we could say generate a landscape, one another layer
generate a castle, and on another layer generate a crowd of people.

To make this work I made a prompt-based layering system in a new
"Scene-to-Image" tab.
You write a a multi-line prompt that looks like markdown, where each
section declares one layer.
It is hierarchical, so each layer can have their own child layers.

Examples: https://imgur.com/a/eUxd5qn
![](https://i.imgur.com/L61w00Q.png)

In the frontend you can find a brief documentation for the syntax,
examples and reference for the various arguments.

Here a short summary:

Sections with "prompt" and child layers are img2img, without child
layers they are txt2img.
Without "prompt" they are just images, useful for mask selection, image
composition, etc.
Images can be initialized with "color", resized with "resize" and their
position specified with "pos".
Rotation and rotation center are "rotation" and "center". 

Mask can automatically be selected by color or by estimated depth based
on https://huggingface.co/spaces/atsantiago/Monocular_Depth_Filter.

![](https://i.imgur.com/8rMHWmZ.png)

# Additional dependencies that are required for this change

For mask selection by monocular depth estimation tensorflow is required
and the model must be cloned to ./src/monocular_depth_estimation/
Changes in environment.yaml:
- einops>=0.3.0
- tensorflow>=2.10.0 

Einops must be allowed to be newer for tensorflow to work.

# Checklist:

- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation

Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
2022-10-02 18:23:37 +01:00
Divided by Zer0
5853f3e1a1
Stable Horde bridge (#1204)
# Adds the bridge code which when enabled turns the webui into a
headless [Stable Horde](https://stablehorde.net) instance

It adds a few new command-line args to be able to pass variables to the
bridge, as well as the possibility to set it via a variables files
`bridgeData.py`.

To start the bridge, one needs to add the `--bridge` argument to their
relauncher.py as well as any horde vars they want to specify.

On top of that this adds the loguru module as well as my tuned loguru
config. This provides a much nicer logging output and provides the
capability to save output to files for issue reports etc. For now only
the bridge is utilizing the nice format, but once it's merged, you can
start replacing `print()` with `logger.xxx()` where appropriate

To make the bridge work, I've had to add defaults to txt2img but this
should not affect anything.


# Checklist:

- [ x ] I have changed the base branch to `dev`
- [ x ] I have performed a self-review of my own code
- [ x ] I have commented my code in hard-to-understand areas
- [ x ] I have made corresponding changes to the documentation

Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
Co-authored-by: Thomas Mello <work.mello@gmail.com>
Co-authored-by: Joshua Kimsey <jkimsey95@gmail.com>
Co-authored-by: ZeroCool <ZeroCool940711@users.noreply.github.com>
2022-10-02 18:22:27 +01:00
Alejandro Gil
dbcad12fd6
Changed the default output folder to be shorter. (#1382) 2022-10-02 09:49:33 -07:00
ZeroCool940711
4e0511dbac Changed the default output folder to be shorter. 2022-10-02 09:46:30 -07:00
Alejandro Gil
0dfab1ad92
Fixed GFPGAN upscaling at the end of the generation as well as doing the face restoration. (#1381)
- Added default values to some functions arguments to make them
optional.
2022-10-02 07:59:14 -07:00
ZeroCool940711
91957dab34 Fixed GFPGAN upscaling at the end of the generation as well as doing the face restoratin.
- Added default values to some functions arguments to make them optional.
2022-10-02 07:54:56 -07:00
Alejandro Gil
6fdbc643e4
Improved the Settings page layout and code structure. (#1379) 2022-10-02 07:00:18 -07:00
ZeroCool940711
02432b4b39 Improved the Settings page layout and code structure. 2022-10-02 06:59:29 -07:00
Alejandro Gil
395a99da26
Add Full Settings Options to Settings.py (#1370)
Started off by adding the Txt2Img settings from the
`configs/webui/webui_streamlit.yaml` file. All are working ~~except
`separate_prompts`, which throws a `Missing key separate_prompts` error
for some reason~~.

Fixed the error.

# Checklist:

- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
2022-10-02 06:26:12 -07:00
Joshua Kimsey
61f0281dac
Merge branch 'dev' into expand-settings-page 2022-10-02 04:25:11 -04:00
Joshua Kimsey
802355b683 Finished Adding Settings Components
Repetitive Actions Are Repetitive
2022-10-02 04:24:50 -04:00
Alejandro Gil
70b4bea3db
Added LDSR to the UI. (#1377)
Unfortunately I think I broke REALESRGAN and it's now enabled by default
even when you deselect the option for it on the UI, have to figure out
what I missed tomorrow when I wake up, the world is not going to end if
you guys have that broken for a single night.
2022-10-01 20:21:45 -07:00
ZeroCool940711
0c03cedeb9 Added LDSR to the UI. 2022-10-01 20:18:09 -07:00
ZeroCool940711
a5ddf9f355 Added LDSR options on the config file. 2022-10-01 19:44:00 -07:00
ZeroCool940711
bbedcc8e84 Merge remote-tracking branch 'origin/dev' into dev 2022-10-01 19:19:04 -07:00
Joshua Kimsey
fc12f124c9
Merge branch 'dev' into expand-settings-page 2022-10-01 21:20:56 -04:00
hlky
59f4826e3e
Update entrypoint.sh 2022-10-02 02:04:31 +01:00
hlky
511730de88
Update entrypoint.sh 2022-10-02 02:03:17 +01:00
ZeroCool940711
3756c1d74c Added option on the UI to select a model for GFPGAN in case we have more than one version on its folder. 2022-10-01 17:43:36 -07:00
hlky
814cf8597c
Update entrypoint.sh 2022-10-02 01:39:09 +01:00
hlky
a3f94d3491
Update txt2vid.py 2022-10-02 00:52:53 +01:00
hlky
babf6c4fc0
Update txt2vid.py 2022-10-02 00:46:51 +01:00
hlky
dd461037a6
Update webui_streamlit.yaml 2022-10-02 00:28:01 +01:00
hlky
4b6de58ae4
Update txt2vid.py 2022-10-02 00:27:58 +01:00
hlky
d017fe7af6
Update modules.py 2022-10-02 00:04:08 +01:00