Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

SUPIR upscaling wrapper for ComfyUI

Using Low-rank adaptation to quickly fine-tune diffusion models.

Demo code of the paper "SegFlow: Joint Learning for Video Object Segmentation and Optical Flow", in ICCV 2017

Numerical renormalization group

Generating Optical Flow Ground Truth with Unreal Engine 4

Unreal Engine plugin for easy creation of synthetic image datasets

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/sp…

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

An Efficient Algorithm for Estimating the Inverse Optical Flow

VideoSys: An easy and efficient system for video generation

Official mirror of Blender

The Cycles Render Engine - official mirror

Open-Sora: Democratizing Efficient Video Production for All

A procedural Blender pipeline for photorealistic training image generation

Labeling extension for Automatic1111's Web UI

Image Aesthetic Assessment in PyTorch with implemented popular datasets and models (possibly providing the pretrained ones).

🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

The official implementation for A2-RL: Aesthetics Aware Rinforcement Learning for Automatic Image Cropping

Image auto crop toolbox. Support any proportion of cropping results, based on face detection and GAIC. 图片智能裁剪工具箱,支持任意比例裁剪结果,基于人脸检测和 GAIC.

Stable Diffusion web UI

MINER: Multiscale Implicit Neural Representation

Unofficial implementation (replicates paper results!) of MINER: Multiscale Implicit Neural Representations in pytorch-lightning

Octree-based 3D Convolutional Neural Networks [SIGGRAPH 2017]