Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs

Documenti analoghi

• Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models
  di: Xu, Bicheng, et al.
  Pubblicazione: (2024)
• All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding
  di: Rahman, Tanzila, et al.
  Pubblicazione: (2026)
• Visual Concept-driven Image Generation with Text-to-Image Diffusion Model
  di: Rahman, Tanzila, et al.
  Pubblicazione: (2024)
• Instant Preference Alignment for Text-to-Image Diffusion Models
  di: Li, Yang, et al.
  Pubblicazione: (2025)
• One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
  di: Liu, Tao, et al.
  Pubblicazione: (2025)