diffusiondb
sd-webui-inpaint-anything
| diffusiondb | sd-webui-inpaint-anything | |
|---|---|---|
| 6 | 10 | |
| 1,116 | 938 | |
| 2.4% | - | |
| 5.5 | 8.7 | |
| 3 months ago | 4 days ago | |
| Python | Python | |
| MIT License | 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.
diffusiondb
- DiffusionDB: A large-scale text-to-image prompt gallery dataset based on Stable Diffusion
-
Where do Lexica and playgroundai get their images?
https://poloclub.github.io/diffusiondb/ contains the dataset both used as a starting point
-
Is there a dataset for generated images by SD or Midjourney?
https://github.com/poloclub/diffusiondb Can be used to access the archived images from the August beta (caution 6.5 TB).
-
"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models", Wang et al 2022 (n=14m)
Actual link: https://poloclub.github.io/diffusiondb/
-
Meet This Artificial Intelligence (AI) Image Dataset Called ‘DIFFUSIONDB,’ That Consists of 2 Million Stable Diffusion Images, And Their Text Prompts And Hyperparameters
Repository
Github: https://github.com/poloclub/diffusiondb
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...
What are some alternatives?
stable-karlo - Upscaling Karlo text-to-image generation using Stable Diffusion v2.
stable-diffusion-webui-rembg - Removes backgrounds from pictures. Extension for webui.
ReVersion - ReVersion: Diffusion-Based Relation Inversion from Images
ai-text-to-audio-latent-diffusion - text-to-audio-latent-diffusion
MetalDiffusion - Stable Diffusion for Intel and Silicon Mac's. Forked from @divamgupta's work
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-Latent-Space-Explorer - Codebase for performing various experiments with Stable Diffusion, supported by the diffusers library.
stable-diffusion-pytorch - Yet another PyTorch implementation of Stable Diffusion (probably easy to read)
Dynamic Prompts - A prompt-engineering extension for Automatic1111 that includes templating, wildcards, and automatic prompt generation
sdxl-demos - Python demos for testing out the Stable Diffusion's XL (SDXL 0.9) model.
Paint-by-Sketch - Stable Diffusion-based image manipulation method with a sketch and reference image
FastSAM - Fast Segment Anything