Introducing Würstchen: Fast Diffusion for Image Generation

Introducing TextImage Augmentation for Document Images

Introducing Hugging Face for Education 🤗

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

Faster assisted generation support for Intel Gaudi

Towards Controllable Image Generation through Representation-Conditioned Diffusion Models

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In thi...