Explore live open-source projects and AI models.

DREAM: Diffusion Rectification and Estimation-Adaptive Models (CVPR 2024)

telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3

Nitro-T is a family of text-to-image diffusion models focused on highly efficient training.

Code for the paper Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

Official PyTorch implementation for "Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations"

Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models

Restoring images of damaged paintings using in-painting. Damaged paintings have discolored patches where the paint has faded or fallen off. This project uses image in-painting to fill and restore these lost regions. The models include context-encoders, GANS, conditional GANS and pixel diffusion.

Minimal multi-gpu implementation of EDM2: "Analyzing and Improving the Training Dynamics of Diffusion Models"

Official implementation of "EndoCoT". Scaling endogenous Chain-of-Thought (CoT) reasoning in diffusion models for complex structured generation.

Pattern Recognition 2025🔥🔥🔥: official code for Visual Style Prompt Learning Using Diffusion Models for Blind Face Restoration