Jonathan Fischoff's repositories
tmp-postgres
Create temporary postgres instances
svd-inpainting
An attempt at a SVD inpainting pipeline
svd-playground
A repo for SVD experiments
next-pose-control-net
ControlNet For Coherent Guided Animations
animatediff-cli
a CLI utility/library for AnimateDiff stable diffusion generation
postgres-options
An Options type for PostgreSQL
svd-tomesd
A repo to test a fork of tomesd that works with StableVideoDiffusionPipeline
AlphaPose
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
clarity-upscaler
Clarity-Upscaler: Reimagined image upscaling for everyone
cython_bbox
standalone cython_bbox borrowed from faster-rcnn
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
ECCV2022-RIFE
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
generative-models
Generative Models by Stability AI
glitch-diffuse
Let's jam an audio spectrum into the SD's prompt embeddings because we can
jfischoff.github.io
A Haskell Blog (mostly) https://jfischoff.github.io
lambda-diffusers
A fork to blend multiple images and a text prompt
memmpy
Software Package for the Maximum Entropy on the Mean (MEM) Method
MultiDiffusion
Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion""
new-supir
another supir fork
PhotoMaker
PhotoMaker
replace-background-sd
Some tests on how to replace the background in Stable Diffusion
super-channel-control-net
This is a prototype ControlNet for Stable Diffusion that uses additional channels for the control image
SUPIR
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild
text-to-image
A single API for text-to-image, built on fal that supports all Stable Diffusion variants
tomesd
Speed up Stable Diffusion with this one simple trick!