[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

DreamOmni2中VLM在ComfyUI中的复现，支持int4,int8量化；配合loras可完成原项目的复现

A ComfyUI node for dvlab-research/DreamOmni2

ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

Official implementation of NerualSVG

Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

[NeurIPS 2025] Efficient Reasoning Vision Language Models

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

[NeurIPS 2024] The official implementation of HairFastGAN. A framework for virtual hairstyle fitting.

Pytorch Implementation of: "Stable-Hair: Real-World Hair Transfer via Diffusion Model" (AAAI 2025)

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

A list of AI autonomous agents

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

verl: Volcano Engine Reinforcement Learning for LLMs

A fork to add multimodal model training to open-r1

A generative world for general-purpose robotics & embodied AI learning.

Official repo and evaluation implementation of VSI-Bench

[ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"

Official repository for VisionZip (CVPR 2025)

A Python library for alpha matting

The world's simplest facial recognition api for Python and the command line

The best OSS video generation models, created by Genmo

A Go implementation in Raft, for 18-845 at CMU (Spring 2015).

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

A collection of resources on controllable generation with text-to-image diffusion models.

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)