Stars
[SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer
A curated list of awesome 3D scene generation papers
[ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
Official implementation of UnifiedReward & UnifiedReward-Think
Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.
Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
GPT4V-level open-source multi-modal model based on Llama3-8B
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
[CVPR 2025 Oral] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
[ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
Improving Video Generation with Human Feedback
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.
Implementation for Describe Anything: Detailed Localized Image and Video Captioning
TAPIP3D: Tracking Any Point in Persistent 3D Geometry
🌍 WorldGen - Generate Any 3D Scene in Seconds
collection of diffusion model papers categorized by their subareas
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
A TTS model capable of generating ultra-realistic dialogue in one pass.
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
MAGI-1: Autoregressive Video Generation at Scale
SkyReels-V2: Infinite-length Film Generative model