Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation

Documenti analoghi

• Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
  di: Gong, Biao, et al.
  Pubblicazione: (2023)
• Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
  di: Huang, Siteng, et al.
  Pubblicazione: (2023)
• Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
  di: Dai, Fengyuan, et al.
  Pubblicazione: (2024)
• Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following
  di: Feng, Yutong, et al.
  Pubblicazione: (2023)
• VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
  di: Liu, Xuyang, et al.
  Pubblicazione: (2023)