Concept Preservation (CP): 0.598Prompt Following (PF): 0.865Overall (CP * PF): 0.517
Papers with Code · CC BY-SA 4.0
Personalized Image Generation
Utilizes single or multiple images that contain the same subject or style, along with text prompt, to generate images that contain that subject as well as match the textual description. Includes finetuning-based methods (e.g. DreamBooth, Textual Inversion) as well as encoder-based methods (e.g. E4T, ELITE, and IP-Adapter, etc.).
논문
Concept Preservation (CP): 0.593Prompt Following (PF): 0.640Overall (CP * PF): 0.380
Concept Preservation (CP): 0.378Prompt Following (PF): 0.624Overall (CP * PF): 0.236
Concept Preservation (CP): 0.547Prompt Following (PF): 0.495Overall (CP * PF): 0.271
Concept Preservation (CP): 0.528Prompt Following (PF): 0.690Overall (CP * PF): 0.364