* added image lab
* first release
model loading/unloading and save procedure added, commented out unused code from frontend
* bug fixes
Changed the image output to a gallery to display multiple items
Fixed results not showing up in output
Fixed RealESRGAN 2x mode not working and hard coded the default value for the reload.
* added GoBig model check
* added LDSR load check
* removed global statements, added model loader/unloader function
* fixed optimized mode
* update
* update
Added send to lab button
Added a print out if latent-diffusion folder isn't found
* brought back the fix faces and upscale in generation tab
* uncommenting img lab flag
* added LDSR instructions
* default imgProcessorTask set to false
* exposed LDSR settings to lab
users need to reclone the LDSR repo to use them.
* Update frontend.py
moving some stuff around to make them more coherent
* restored upscale and fix faces to img2img
* added notice section
* fixed gfpgan/upscaled pictures not showing in 2img interfaces
* send to lab button now sends info as well
* uncommented dimension info update
* added increment buttons to sampler for that k_euler_a action
* image lab settings toggle on and off with selection
* removed wip settings panel
* better model loading handling and removed increment buttons
* explaining
* disabled SD unloading in image lab upscaling with realesgan and face fix
* fixed a conflict with image lab
Co-authored-by: dr3amer <91037083+dr3am37@users.noreply.github.com>
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
This adds a text box to Image Lab that displays the metadata
of any PNG files dropped on it. Can be used to read the info
saved with --save-metadata
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* Changed relauncher.py to have easier to set arguments for users, added inbrowser as an argument choice
Changed `relauncher.py` to have easier to set argument parameters for users to change. No longer is editing the main `os.system` string needed. Now, users can choose to set some of the commonly used arguments (totally open to more additions here) to be True or False, with an added area for users to enter their own custom arguments as desired.
This really should make it easier for users to toggle what parameters they wish to launch with, and prevents them from needing to edit the main launch string for the `webui.py` file.
Addition changes to `relauncher.py` include increasing the relaunch time from 0.5 seconds to 1 second, to allow for easier program closing from the Terminal.
Changed `webui.py` to now include an `--inbrowser` argument to open the interface automatically in a user's default browser. The default is set to `False`. Gradio params have also now been alphabetised. A notice was given to users waiting for port 7860 to open that it may take upwards of 60 seconds to become available.
* Added comments to describe what the changeable common arguments in relauncher.py do
* Changed relauncher.py to fit with requested changes
Added timeout for relauncher loop
Changed inbrowser argument variable to be more understandable
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* Add max-jobs command line argument
Adds a new command line argument, max-jobs, which will set the number
of concurrent jobs the gradio queue will allow. When set to more than
the default of 1 the gradio UI will be able to process additional
UI commands at the same time.
* JobManager: initial txt2img implementation
Initial implementation of JobManager, applied to txt2img.
Adds 'refresh' and 'cancel' buttons to the UI. These are useful when
generating images with large batch counts. The 'refresh' button will
update the gallery with the currently-generated images, and the cancel
button will cause the generation to stop after the current iteration.
The new job manager can be disabled with the parameter
--no-job-manager
* JobManager: Add status update text
* JobManager: Replace wrapped inputs as well
* JobManager: Per-session unique keys
* JobManager: Pre and Post call funcs, UI updates
Added pre- and post- function call 'dummy objects' to allow updating
the UI before and after a generate run. Update the visuals of the
buttons and status text in these new functions.
* JobManager: enforce maximum jobs
* JobManager: Move 'call' func code block
It just makes more sense between _pre and _post.
* JobManager: Add session management
Adds support for multiple browser sessions.
A single session cannot run the same job twice.
If there are no available jobs when Generate is clicked, the
generation aborts. It does *not* queue.
* JobManager: add session maintenance
Addded the ability for one session to stop all concurrent sessions,
and to free memory from any 'finished' sessions for which the
browser has been closed (as the images will be stored until the
browser does a final 'refresh' after the job finishes, which will
never happen if the browser closed)
* JobManager: Add img2img support
This *should* add JobManager to img2img, but it is untested
since img2img is broken for me even without my changes.
* Fixed img2img functionality on this pr
* Revert "Fixed img2img functionality on this pr"
This reverts commit 649b1e8e65.
* Img2Img: Fix 'image editor' options not visible
* Fix Img2Img Job Manager integration
* Img2Img UI: Move JobManager above Image Actions
It is helpful if it is on the screen when you hit generate, so
you can notice the button light up when generation starts.
* Improve job status text
* JobManager: Free available job on exception
* JobManager: Add queueing
Adds a simple queueing system to JobManager. If max-jobs concurrent
jobs are already active then any subsequent jobs will block until
a slot frees up.
Note: The UI does not give great feedback to this. The JobManager
status box will say "Loading..."
* JobManager: Fix queue accidentally LIFO
Queues should really be first in, first out.
* JobManager: add draw_gradio_ui function
Reduces a lot of boilerplate code in frontend.py
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* Added abilty to log prompts and info to one file instead of several
This is my first pull request be gentle I made changes so instead of having several files with prompts with one for each file you can just have one file with the prompt info I also made sure the prompts would work with params in prompts
* Add files via upload
* Fixed Image to image not working
* Add files via upload
* Revert "Add files via upload"
This reverts commit bb10b632bf.
* updated log
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* added image lab
* first release
model loading/unloading and save procedure added, commented out unused code from frontend
* bug fixes
Changed the image output to a gallery to display multiple items
Fixed results not showing up in output
Fixed RealESRGAN 2x mode not working and hard coded the default value for the reload.
* added GoBig model check
* added LDSR load check
* removed global statements, added model loader/unloader function
* fixed optimized mode
* update
* update
Added send to lab button
Added a print out if latent-diffusion folder isn't found
* brought back the fix faces and upscale in generation tab
Co-authored-by: dr3amer <91037083+dr3am37@users.noreply.github.com>
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* Merge with master
* params in prompt WIP
Signed-off-by: Alex Volkov <alex.volkov@fundbox.com>
* Added highligted text output, added copy and pastable dynamic params
Signed-off-by: Alex Volkov <alex.volkov@fundbox.com>
* Fixes with working repo
Signed-off-by: altryne <altryne@gmail.com>
* some fixes
Signed-off-by: Alex Volkov <alex.volkov@fundbox.com>
Signed-off-by: altryne <altryne@gmail.com>
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* added image lab
* first release
model loading/unloading and save procedure added, commented out unused code from frontend
* bug fixes
Changed the image output to a gallery to display multiple items
Fixed results not showing up in output
Fixed RealESRGAN 2x mode not working and hard coded the default value for the reload.
* added GoBig model check
* added LDSR load check
* removed global statements, added model loader/unloader function
* fixed optimized mode
* update
Co-authored-by: dr3amer <91037083+dr3am37@users.noreply.github.com>
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* Fixed ports not opening on 7860
Fixed the issue where, after a crash or quick relaunch, SD would not use the same port. It will now wait for 7860 to reopen before launching the webui again.
* Added ability to choose custom port at launch
Added a parser argument to allow users to choose a custom port at launch. Default is still 7860. Also ensured that error messages associated with a port not being available will reflect what port is actually being checked.
* Moved parser argument for port to be under the share parser argument
Moved the port parser argument to be directly under the share parser argument for consistency.
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* added image lab
* first release
model loading/unloading and save procedure added, commented out unused code from frontend
* bug fixes
Changed the image output to a gallery to display multiple items
Fixed results not showing up in output
Fixed RealESRGAN 2x mode not working and hard coded the default value for the reload.
* added GoBig model check
* added LDSR load check
* removed global statements, added model loader/unloader function
Co-authored-by: dr3amer <91037083+dr3am37@users.noreply.github.com>
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* refactor js interface
* rename call_SD to call_JS
* add invocation example to call_JS
* serialize args before passing them to js
* allow override of x
currently will endless loop in the while: time.sleep(1) part on 2nd iteration of for loop.
move back to cpu should only be ran once afterwards not [batchsize] times.
Co-authored-by: hlky <106811348+hlky@users.noreply.github.com>
* fix: add guard against subprompt weights adding up to zero
* feat: add support for backslash-escaped colon character in prompts
Co-authored-by: _nderscore <_@_._>
