Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding（书生 · 妙析多模态美学理解大模型）

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

A Preliminary Exploration Towards General Image Restoration

Lumina-T2X is a unified framework for Text to Any Modality Generation

Unifying Image Processing as Visual Prompting Question Answering

The pure and clear PyTorch Distributed Training Framework.

Python package to corrupt arbitrary images.

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

Open-Sora: Democratizing Efficient Video Production for All

A Python package that uses task-based neurons to build neural networks.

Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy

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

VMamba: Visual State Space Models，code is based on mamba

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.

A latent text-to-image diffusion model

ECCV2024：A Comparative Study of Image Restoration Networks for General Backbone Network Design

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

Synthetic Image Detection

ICLR 2024 (Spotlight) - SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

Official implementation of SAM-Med2D

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior