Repository Index

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

• 3d
• 3d-aigc
• 3d-generation
• image-to-3d

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

• diffusion-models
• high-resolution
• sparse-attention
• video-generation

Official Hi3D v1.0: high-resolution 3D geometry refinement built on Sparc3D. Inference code, model weights, and documentation.

• 3d-generation
• image-to-3d
• geometry-refinement
• sparc3d

[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"

• diffusion-transformers
• eccv2026
• image-generation
• training-free

Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"

• diffusion-models
• efficient-inference
• high-resolution
• image-generation