ADT: Tuning Diffusion Models with Adversarial Supervision

Documenti analoghi

• CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
  di: Jiang, Dongzhi, et al.
  Pubblicazione: (2024)
• EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
  di: Zong, Zhuofan, et al.
  Pubblicazione: (2024)
• MoVA: Adapting Mixture of Vision Experts to Multimodal Context
  di: Zong, Zhuofan, et al.
  Pubblicazione: (2024)
• Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
  di: Ma, Bingqi, et al.
  Pubblicazione: (2024)
• Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
  di: Shen, Dazhong, et al.
  Pubblicazione: (2024)