sd-webui-segment-anything
Inpaint-Anything
sd-webui-segment-anything | Inpaint-Anything | |
---|---|---|
17 | 5 | |
3,242 | 5,648 | |
- | - | |
6.3 | 7.0 | |
about 1 month ago | 3 months ago | |
Python | Jupyter Notebook | |
- | Apache License 2.0 |
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-segment-anything
-
Textual inversion. The best way to prepare photos of a person?
One idea would be to use Segment Anything to cut out the character/face from the background and then replace with random backgrounds that you generate with stable diffusion. Here's an extension for Automatic1111 :) https://github.com/continue-revolution/sd-webui-segment-anything
-
How hard is it to "code" a tool based on segment-anything and Stable diffusion ?
Checkout this code https://github.com/continue-revolution/sd-webui-segment-anything
- Can I use Interrogate CLIP or something similar to get image position data?
- Best way to mask images automatically?
-
Information is currently available.
Segment anything is the extension that you're looking for.
- What's your favorite small tweaks to make? I'll go first
-
Show HN: Image background removal without annoying subscriptions
If anyone is already running auto1111, or simply uninterested in paying, there's an addon that does this very well available here https://github.com/KutsuyaYuki/ABG_extension, additionally I've had very good results using the masks generated by Facebook's SAM, which is also available as an addon here https://github.com/continue-revolution/sd-webui-segment-anyt...
- The main reason why people will keep using open source vs Photoshop and other big-tech generative AIs
-
Stable Diffusion + Segment Anything App and Tutorial
There’s an A111 extension already that I think does the same thing (I’ve had it installed for a few weeks now). https://github.com/continue-revolution/sd-webui-segment-anything
-
YourVision: Stable Diffusion + Segment Anything
use this and inpainting https://github.com/continue-revolution/sd-webui-segment-anything
Inpaint-Anything
-
Character Isolation
I'm not sure I've actually understood your question, but if you're using A1111 webui perhaps the Inpaint-Anything extension is what you are looking for. It can automatically mask subjects from the background for inpainting.
-
Auto Inpainting: Is there an extension that can auto inpaint an area (e.g. with help of Openpose, or object detection) to change many batches of images?
The Inpaint Anything extension combines "Segment Anything"'s ability to detect and tag objects with auto-masking and inpainting.
-
Stable Diffusion + Segment Anything App and Tutorial
yes definitely some insparation and from the inpaint anything project (https://github.com/geekyutao/Inpaint-Anything)
- Inpaint from a Sample Image to Fill the Mask
-
META's Segment Anything + Inpainting
Code: https://github.com/geekyutao/Inpaint-Anything
What are some alternatives?
stable-diffusion-webui-wd14-tagger - Labeling extension for Automatic1111's Web UI
stable-diffusion-webui-rembg - Removes backgrounds from pictures. Extension for webui.
edit-anything-app - The source of the demo app for fal-serverless + Next.js
stable-diffusion-webui-amdgpu - Stable Diffusion web UI
stable-diffusion-webui - Stable Diffusion web UI
ddetailer
EditAnything - Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
segment-anything - The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Auto-Photoshop-StableDiffusion-Plugin - A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using either Automatic or ComfyUI as a backend.
sd-webui-segment-everything - Segment Anything for Stable Diffusion Webui [Moved to: https://github.com/continue-revolution/sd-webui-segment-anything]