[ICLR 2026 🔥 ] Official implementation of "UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing"

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…

Official Implementation of Paper Transfer between Modalities with MetaQueries

[CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

Official implementation of BLIP3o-Series

Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)

Code for Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense? [COLM 2024]

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Fast and memory-efficient exact attention

[ICLR 2025 Oral] On Scaling Up 3D Gaussian Splatting Training

Unofficial implementation of "SODA: Bottleneck Diffusion Models for Representation Learning"

Your image is almost there!

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

PDM-based Purifier

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

A conda-forge distribution.

Infinite Photorealistic Worlds using Procedural Generation

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

Official implementation of AnimateDiff.

Grok open release

DeepSeek-VL: Towards Real-World Vision-Language Understanding

TripoSR: Fast 3D Object Reconstruction from a Single Image

DUSt3R: Geometric 3D Vision Made Easy

Efficient, check-pointed data loading for deep learning with massive data sets.