SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.

StoryMaker: Towards consistent characters in text-to-image generation

Code for the SIGGRAPH Asia 2023 paper "Intrinsic Harmonization for Illumination-Aware Compositing"

Kolmogorov-Arnold Transformer: A PyTorch Implementation with CUDA kernel

Multiple Transformation Function Estimation for Image Enhancement

Library of Python functions for various types of image enhancement

An algorithm based on decision trees and deep learning models to enhance images

Deep Learning for Image Enhancement

Automatic LUT creator for OBS using Color Reference Cards for Calibration

Given an input RGB image, we generate novel viewpoints that simulate a 3D interactive experience.

An editing tool for depth images to enable artistic control for creative content creation.

Repo for the paper "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023)

TEED: Tiny and Efficient Edge Detector

ControlNet collections for Flux1-dev model, Trained by TheMisto.ai Team

Various AI scripts. Mostly Stable Diffusion stuff.

Implementation of the Aurora model for atmospheric forecasting

MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning

Colour Science for Python

Pythonic AI generation of images and videos

A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

Environment light tools.

Marching cubes (and related tools) for Python

[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

🌊 Image to → 2.5D Parallax Effect Video. A Free and Open Source ImmersityAI alternative