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

Official Implementation of ICLR'24: Kosmos-G: Generating Images in Context with Multimodal Large Language Models

🔥🔥🔥A curated list of papers on recent diffusion-based high-resolution image and video synthesis works.

Understand Human Behavior to Align True Needs

"Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis" (ECCV 2024)

a research paper for generative cartoon interpolation

More relighting!

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024)

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Your image is almost there!

Fast Diffusion Models with Transformers

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"

The official implementation of DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis

Visualization of DiT self attention features

IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Diffusion Model-Based Image Editing: A Survey (arXiv)

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

DUSt3R: Geometric 3D Vision Made Easy

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Code for DesignEdit

Consistency Models Made Easy

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

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