stable-diffusion
nataili
stable-diffusion | nataili | |
---|---|---|
6 | 4 | |
67 | 89 | |
- | - | |
10.0 | 10.0 | |
over 1 year ago | about 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
stable-diffusion
- Stable Inference (k-samplers, multicond, inpainting) and YASD Discord Bot now support Stable Diffusion 2
-
Morphing auto-captioned images between each other or "art2art", code in comments
I used my own SD repo, but it should easily be portable to others, and the captioning step and be automated. There is current an issue open on the automatic1111 repo, if you found it neat.
-
[hlky’s/sd-webui] Announcing Sygil.dev & Project Nataili
fwiw I have my own implementation of the pipeline that is running over an n-many scalable gRPC implementation through jina flow, and I personally think that making the gRPC API first class with an implementation of CompVis stable-diffusion is a mistake.
-
Outpainting and inpainting (via clipseg) with the latest RunwayML 1.5 weights and VAE is out of beta and live on the LAION Discord Server
My stable-diffusion fork
-
There is a new model that brings SD inpainting/outpainting onto the level of Dall-E2. Thanks for Runway to make it open for everyone.
Thanks for the mention! The branch you're probably looking for is here. The code is pretty simple if you want to play with it:
nataili
-
🚀 🚀 Fastest SD inference + webUI (Open Source) with voltaML. Accelerate 20xx, 30xx GPUs to the fastest speed!! 🔥🔥
Very nice! The Stable Horde relies on a free software backend as well which aim to become an accessible SD framework for everyone. I'd love to be able to onboard your improvements as an official component and supercharge the stable horde for everyone in the world.
-
A warning about Unstable Diffusion
among other things they are developing distributed training: https://github.com/Sygil-Dev/nataili
-
The Stable Horde now supports img2img as well as multiple models available at the same time. And we just added SD 1.5
Unfortunately it uses an old version of diffusers. I opened an issue in case someone wants to onboard it: https://github.com/Sygil-Dev/nataili/issues/21
-
[hlky’s/sd-webui] Announcing Sygil.dev & Project Nataili
Shiny New Common Backend you can contribute to, Sygil.dev is the new hlky’s, black is still black cause black is timeless.
What are some alternatives?
AI-Horde - A crowdsourced distributed cluster for AI art and text generation
stable-diffusion - Latent Text-to-Image Diffusion
stable-diffusion-grpcserver - An implementation of a server for the Stability AI Stable Diffusion API
CrossAttentionControl - Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion
git-it-electron - :computer: :mortar_board: Git-it is a (Mac, Win, Linux) Desktop App for Learning Git and GitHub
g-diffuser-bot - Experimental utilities, extensions, and frontend interfaces for the diffusers library (stable-diffusion) [Moved to: https://github.com/parlance-zz/g-diffuser-lib]
yasd-discord-bot - Yet Another Stable Diffusion Discord Bot
dalle-flow - 🌊 A Human-in-the-Loop workflow for creating HD images from text
stable-diffusion-webui - Stable Diffusion web UI
stable-core - The stable-core project is your personal server for AI rendering, powered with community plugins