real time face swap and one-click video deepfake with only a single image (uncensored)

Official inference repo for FLUX.1 models

Official repository for the paper PLLaVA

Utilities intended for use with Llama models.

Create Magic Story!

ControlNet++: All-in-one ControlNet for image generations and editing!

Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

[ECCV 2024] Be-Your-Outpainter https://arxiv.org/abs/2403.13745

Android real-time display control software

[CVPR2024] Diffusion-based Blind Text Image Super-Resolution (Official)

[ECCV2024] An official pytorch implement of the paper "MambaIR: A simple baseline for image restoration with state-space model".

Efficient computing methods developed by Huawei Noah's Ark Lab

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

CV-VAE: A Compatible Video VAE for Latent Generative Video Models

Official repository of MLLA

Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"

Boosting the performance of consistency models with PCM!

SigLIP-based Aesthetic Score Predictor

Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training

Visualization of DiT self attention features

MambaOut: Do We Really Need Mamba for Vision?

HQ-Edit: A High-Quality and High-Coverage Dataset for General Image Editing

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

More relighting!

Stable Video Diffusion Training Code and Extensions.