Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings

Documenti analoghi

• Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
  di: Moayeri, Mazda, et al.
  Pubblicazione: (2024)
• PRIME: Prioritizing Interpretability in Failure Mode Extraction
  di: Rezaei, Keivan, et al.
  Pubblicazione: (2023)
• On Mechanistic Knowledge Localization in Text-to-Image Generative Models
  di: Basu, Samyadeep, et al.
  Pubblicazione: (2024)
• Localizing Knowledge in Diffusion Transformers
  di: Zarei, Arman, et al.
  Pubblicazione: (2025)
• Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
  di: Balasubramanian, Sriram, et al.
  Pubblicazione: (2024)