SD_API UI additions for SD workflow #1006
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
updated the ui to select models hr fix and now is easier to set things directly on Ooga I need to see those vram management, the thing to down_res the preview in chat is not working for me I try fixing it but Idk will add a way to select vaes and loras if I find where to get them from the api
Made a separate button to apply the model it saves time not loading the same model each time you regenerate. I will put all these persistent settings in the same compartment within the row. I don't know if I need to update something, but the VRAM management can't load and unload the checkpoints for me. Also, the Resize preview is not working :(
|
I changed the name so is easier to see I made a video working with the SD_api https://youtu.be/wenmSXqUDPo I love this thing |
extensions/sd_api_pictures/script.py
Outdated
| } | ||
|
|
||
| print(f'Prompting the image generator via the API on {params["address"]}...') | ||
| response = requests.post(url=f'{params["address"]}/sdapi/v1/txt2img', json=payload) | ||
| response.raise_for_status() | ||
| r = response.json() | ||
|
|
||
| # This is broken for me please check where I messed up. I am sorry. |
extensions/sd_api_pictures/script.py
Outdated
| sd_model_checkpoint = gr.Dropdown(label="model", choices=sd_models) | ||
| sampler_index = gr.Dropdown(label="sampler", choices=samplers) | ||
|
|
||
| with gr.Accordion("Prompt settigns", open=False): |
There was a problem hiding this comment.
typo here on settings and above (325) on Apply
changed sampler name fixed the apply typo
only batch size commented out I am getting duplicates maybe seed-1 and subseed -1 are not passing?
oobabooga
added
the
extensions
Batch count, Batch size, clip skip, interactive mode SD prompt of command, saves .txt with generation parameter, save stealth info on .png and respects interactive address. stealth info needs https://github.com/ashen-sensored/sd_webui_stealth_pnginfo installed on A1111 webui to work
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Updated models, samplers, upscaler hi res fix, denoise strength, minimal changes to the code will add a way to select VAEs and loRas if I find where to get them from the SD_api #batch size is working but I commented out because is duplicating the images, maybe some bug on the seed parameters. https://youtu.be/kAUQ04iNfjI