Stars
NOVA: Autoregressive Video Generation without Vector Quantization
HunyuanVideo: A Systematic Framework For Large Video Generation Model
[NeurIPS 2024] Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
Efficient vision foundation models for high-resolution generation and perception.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
🏠[ECCV 2024] GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
[ECCV 2024] GVGEN: Text-to-3D Generation with Volumetric Representation
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Official Pytorch implementation of "Visual Style Prompting with Swapping Self-Attention"
[ECCV 2024] Official implementation of the paper "GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views"
Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
CSGO: Content-Style Composition in Text-to-Image Generation 🔥
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
[AAAI 2025🔥] Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
[ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
Official implementation of Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
Open-Sora: Democratizing Efficient Video Production for All
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
A game engine powered by python and panda3d.
Code repository for T2V-Turbo and T2V-Turbo-v2
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models