Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Documenti analoghi

• Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis
  di: Aubreville, Marc, et al.
  Pubblicazione: (2024)
• Scaling Down Text Encoders of Text-to-Image Diffusion Models
  di: Wang, Lifu, et al.
  Pubblicazione: (2025)
• Effortless Vision-Language Model Specialization in Histopathology without Annotation
  di: Qiu, Jingna, et al.
  Pubblicazione: (2025)
• Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers
  di: Yang, Chaojie, et al.
  Pubblicazione: (2026)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
  di: Gong, Chao, et al.
  Pubblicazione: (2024)