SD.Next: Advanced Implementation of Stable Diffusion
Updated
Stable Diffusion web UI
Updated
Adds a configurable dropdown to allow you to change UI preset settings in the txt2img and img2img tabs.
Updated
Img2img batch interrogator for AUTOMATIC1111's Stable Diffusion web UI
Updated
The Inpaint Anything extension performs SD inpainting, cleaner, ControlNet inpaint, and sending a mask to img2img, using a mask selected from the segmentation output of Segment Anything.
Updated
Allows you to include various shortcodes in your prompts. You can pull text from files, set up your own variables, process text through conditional functions, and so much more - it's like wildcards on steroids. It now includes integrations like hard-prompts made easy, ControlNet, txt2img2img and txt2mask.
Updated
Extension for creating videos using img2img and ebsynth. Output edited videos using ebsynth. Works with ControlNet extension.
Updated
Take a png image, generate a background and mask, then send it to img2img to generate a new backgrou
Updated
Add a delete button for txt2img and img2img using Send2Trash
Updated
A basic img2img script that will dump frames and build a video file. Suitable for creating interesting zoom-in warping movies. This is intended to be a versatile toolset to help you automate some img2img tasks.
Updated
Provides more options for latent upscale in img2img, surpassing those offered by Hires Fix for the txt2img process.
Updated
Runs txt2img, img2img, highres-fix at increasing dimensions and batch sizes until OOM, and outputs data to graph.
Updated
A script for img2img that extract a gif frame by frame for img2img generation and recombine them back into an animated gif
Updated
Create masks for img2img based on a depth estimation made by MiDaS.
Updated
These scripts allow for dynamic CFG control during generation steps. With the right settings, this could help get the details of high CFG without damaging the generated image even with low denoising in img2img.
Updated
It is a depth aware extension that can help to create multiple complex subjects on a single image. It generates a background, then multiple foreground subjects, cuts their backgrounds after a depth analysis, paste them onto the background and finally does an img2img for a clean finish.
Updated