diffusion-transformer

HunyuanVideo: A Systematic Framework For Large Video Generation Model

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

🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

OpenMusic: SOTA Text-to-music (TTM) Generation

Implementation of F5-TTS in MLX

Taming FLUX for Image Inversion & Editing; HunyuanVideo for Video Inversion & Editing! (Official implementation for Taming Rectified Flow for Inversion and Editing.)

FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

[ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy

Project Page repo of OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication

Adaptive Caching for Faster Video Generation with Diffusion Transformers

The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"

Implementation of F5-TTS in Swift using MLX

ArXiv paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151

Implementation of Diffusion Transformer Model in Pytorch

FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.

Implementation of RIFT-SVC, a singing voice conversion model based on Rectified Flow Transformer.

This repo implements Diffusion Transformers(DiT) in PyTorch and provides training and inference code on CelebHQ dataset