sd-webui-inpaint-anything
adetailer
sd-webui-inpaint-anything | adetailer | |
---|---|---|
10 | 43 | |
938 | 3,727 | |
- | - | |
8.7 | 9.5 | |
9 days ago | 6 days ago | |
Python | Python | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sd-webui-inpaint-anything
-
How to send masked photo to img2img inpainting
Hey everyone,Today I installed inpaint-anything extension from github(https://github.com/Uminosachi/sd-webui-inpaint-anything) to Stable Diffusion. It works perfectly.
- Human masking
-
Fast Segment Anything (40ms/image)
I'm a huge fan of "Inpaint Anything" for its implementation of "Segment Anything". I'd anticipate an update from the developer asap - pretty active. https://github.com/Uminosachi/sd-webui-inpaint-anything
-
Any way to keep the transparency of a png after running it through img2img/inpaint?
"Inpaint Anything" is an unlisted SD extension (not on the in app list yet for some reason) that can export masks (alpha included) w/ transparency. Not sure if it fits your original needs for inpainting, but it may actually be easier. It creates it's own tab: https://github.com/Uminosachi/sd-webui-inpaint-anything
-
Unable to install Inpaint Anything for Stable Diffusion Web UI on a Mac
GitCommandError: Cmd('git') failed due to: exit code(128) cmdline: git clone -v --filter=blob:none -- https://github.com/Uminosachi/sd-webui-inpaint-anything.git in the URL for extension's git repository /Applications/Stable Diffusion/stable-diffusion-webui/tmp/sd-webui-inpaint-anything in the URL for extension's git repository stderr: 'Cloning into '/Applications/Stable Diffusion/stable-diffusion-webui/tmp/sd-webui-inpaint-anything in the URL for extension's git repository'... fatal: unable to access 'https://github.com/Uminosachi/sd-webui-inpaint-anything.git in the URL for extension's git repository/': URL using bad/illegal format or missing URL '
-
HELP! What options/extensions are available for auto masking in A1111?
you could use this extension https://github.com/Uminosachi/sd-webui-inpaint-anything
- Favorite InPaint Tool? ControlNet, Inpaint Anything, Photoshop, or other?
- Inpaint Anything (uses "Segment Anything") - Cool A1111 Extension not (yet) on the in App list
-
Setting Environment Variables to Avoid Memory Errors
When I try to use Inpaint Anything, I get this error...
adetailer
- WHY IS THIS HAPPENING MAKE IT STOP I HATE IT
-
Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
https://github.com/Bing-su/adetailer works very well on faces and hands.
This is a good solution for all the use cases I’ve dealt with.
Are there widespread use cases where, knowing a deformity exists is required than just fixing the deformities?
- Automatically skip GFPGAN on faces that are "too low quality"
-
How to diffuse better faces?
Ive found using ADetailer (https://github.com/Bing-su/adetailer, using their reccomended advanced settings and face_yolov8n.pt) and Dynamic Thresholding (CFG set to 12 and Mimic to 7) has vastly improved my face renders. (https://github.com/mcmonkeyprojects/sd-dynamic-thresholding) GL!
- Is there anything which automatically recognizes when something was ill-generated (such as a face, or fingers etc.) and automatically applies the inpainting mask to that area?
-
In the Automatic1111 Web UI, is it possible to get ADetailer working inside Deforum?
ADetailer: https://github.com/Bing-su/adetailer
- Mind-blowing results (LORA/Checkpoint mix)
-
Faces look strange with multiple people
After Detailer will give each of their faces a facelift
-
A little bit of party after fighting each other in Smash bros (Text2img, controlnet, regional prompter, adetailer)
this is amazing and easy workflow for production, but the lora part of adetailer never works for me, i don't know why
- Creating a randomized crowd with various expression through txt2img with adetailer + dynamic prompt extension
What are some alternatives?
stable-diffusion-webui-rembg - Removes backgrounds from pictures. Extension for webui.
ComfyUI_Cutoff - cutoff implementation for ComfyUI
ai-text-to-audio-latent-diffusion - text-to-audio-latent-diffusion
ddetailer
StableFusion - Transform text into images and images into new ones using AI. Our user-friendly web app, built with Diffusion, Python, and Streamlit, offers customizable outputs in various styles and formats
stable-diffusion-webui-composable-lora - This extension replaces the built-in LoRA forward procedure.
stable-diffusion-pytorch - Yet another PyTorch implementation of Stable Diffusion (probably easy to read)
stable-diffusion-webui-two-shot - Latent Couple extension (two shot diffusion port)
sdxl-demos - Python demos for testing out the Stable Diffusion's XL (SDXL 0.9) model.
ultimate-upscale-for-automatic1111
FastSAM - Fast Segment Anything
sd-dynamic-prompts - A custom script for AUTOMATIC1111/stable-diffusion-webui to implement a tiny template language for random prompt generation