PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

PixArt-Σ：4K文本到图像生成的扩散Transformer的由弱到强的训练.

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors

OmniCount：具有语义几何先验的多标签目标计数.

InstanceDiffusion: Instance-level Control for Image Generation

InstanceDiffusion：图像生成的实例级控制.

LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation

LayoutDiffuse：调整基础扩散模型实现布局到图像生成.

Adding Conditional Control to Text-to-Image Diffusion Models

向文本到图像扩散模型添加条件控制.

ReCo: Region-Controlled Text-to-Image Generation

ReCo: 区域控制的文本到图像生成.