edge-connect
g-diffuser-bot
| edge-connect | g-diffuser-bot | |
|---|---|---|
| 1 | 13 | |
| 2,474 | 134 | |
| - | - | |
| 4.1 | 10.0 | |
| 3 months ago | over 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | MIT License |
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.
edge-connect
-
Huge out-painting in 1 step without erased colors or pre-selecting images
It inspired me to search for other ways to fill the white space in outpainting. I found Edge Connect and hacked it in as well. Some basic output can be seen here:
g-diffuser-bot
-
Stable Diffusion Infinite Zoom, Zlikwid Lightning.
I custom trained a model on my artwork using Dreambooth and then used it for infinite zoom using this https://github.com/parlance-zz/g-diffuser-bot/tree/0d3a239cd97762f0646ca9137e543809d890daed
-
Smooth infinite zoom
My project is here: https://github.com/parlance-zz/g-diffuser-bot
-
Out-painting Mk.3 Demo Gallery
This gallery of images was out-painted using the g-diffuser-bot (https://github.com/parlance-zz/g-diffuser-bot)
- List of SD Tutorials & Resources
-
[hlky’s/sd-webui] Announcing Sygil.dev & Project Nataili
It's currently used for the Idea2Art UI and the g-diffuser bot.
-
getimg.ai - I've made outpainting/inpainting editor publicly available
I'm testing it right now and the inpainting/outpainting is impressive. Are you using parlance's fourier-shaped noise out-painting for latent diffusion models method? https://github.com/parlance-zz/g-diffuser-bot
- Best Local Command-Line SD (non-optimized)?
-
xformers coming to Automatic1111
Likewise it is available in the g-diffuser discord bot or interactive CLI here, g-diffuser is built on-top of the GRPC server project: https://github.com/parlance-zz/g-diffuser-bot
- Huge out-painting in 1 step without erased colors or pre-selecting images
-
G-Diffuser-Bot In-painting Demo Reel
Yes, the code is here now: https://github.com/parlance-zz/g-diffuser-bot/tree/g-diffuser-bot-diffuserslib-beta
What are some alternatives?
co-mod-gan - [ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
Umi-AI-Embeds - Wildcards and Code for the Umi AI Engine
CelebV-HQ - [ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
Anime2Sketch - A sketch extractor for anime/illustration.
g-diffuser-lib - Discord bot and utilities for the diffusers library (stable-diffusion) [Moved to: https://github.com/parlance-zz/g-diffuser-bot]
stereo-image-generation - This repository contains code to generate stereo (Side by side) image from a single image.
stable-diffusion-webui - Stable Diffusion web UI
image-ai-utils-server
progrock-stable - Stable Diffusion with some Proggy Enhancements
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
a1111-sd-webui-tagcomplete - Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI