Universal Monocular Metric Depth Estimation

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Janus-Series: Unified Multimodal Understanding and Generation Models

[ECCV‘24] Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

verl: Volcano Engine Reinforcement Learning for LLMs

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

[CVPR 2025] This is an official inference code of the paper "BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation" . Project page: https://bizgen-msra.github.io/

Training code for CLIP-FlanT5

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

Vector (and Scalar) Quantization, in Pytorch

Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control

A framework streamlining Training, Finetuning, Evaluation and Deployment of Multi Modal Language models

Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".

Taming Transformers for High-Resolution Image Synthesis

Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

Awesome autoregressive vision foundation models

Rectified Flow Inversion (RF-Inversion) - ICLR 2025

Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

This is the official testing code of the baseline method presented at the CVPR 2023 NTIRE Real-Time 4K Super-Resolution Challenge. We provide model and pre-trained checkpoints.

A linear estimator on top of clip to predict the aesthetic quality of pictures