🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

Fast and memory-efficient exact attention

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing.

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Official implementation of "Single Image Iterative Subject-driven Generation and Editing".

[ICLR2025] A versatile image-to-image visual assistant, designed for image generation, manipulation, and translation based on free-from user instructions.

A minimal and universal controller for FLUX.1.

[Arxiv'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

[AAAI2025] Textualize Visual Prompt for Image Editing via Diffusion Bridge

Training-Free Text-Guided Image Editing Using Visual Autoregressive Model

Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing

Official Implementation of Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

MAGI-1: Autoregressive Video Generation at Scale

An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Implementation of paper EditCLIP: Representation Learning for Image Editing

Official code of SmartEdit [CVPR-2024 Highlight]