Official PyTorch Implementation of "Scalable Autoregressive Image Generation with Mamba"

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

The paper collections for the autoregressive models in vision.

A suite of image and video neural tokenizers

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

SEED-Voken: A Series of Powerful Visual Tokenizers

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

CUDA accelerated rasterization of gaussian splatting

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

The AI Code Editor

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

🏠[ECCV 2024] GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

Official implementation for "Break-A-Scene: Extracting Multiple Concepts from a Single Image" [SIGGRAPH Asia 2023]

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

A general fine-tuning kit geared toward diffusion models.

Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"

A Data Streaming Library for Efficient Neural Network Training

A native PyTorch Library for large model training

Transform datasets at scale. Optimize datasets for fast AI model training.

Train high-quality text-to-image diffusion models in a data & compute efficient manner

⏬ Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)

Implementation of Autoregressive Diffusion in Pytorch

⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025)

Quantized training of Stable Diffusion 3 Medium to significantly reduce memory usage.

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

Audio Dereverberation with Implicit Neural Representations (INRs)