OpenCodePapers

personalized-image-generation-on-dreambench

Personalized Image Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeOverall (CP * PF)Concept Preservation (CP)Prompt Following (PF)ModelNameReleaseDate
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation✓ Link0.5170.5980.865DreamBooth LoRA SDXL v1.02022-08-25
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models✓ Link0.3800.5930.640IP-Adapter ViT-G SDXL v1.02023-08-13
Generative Multimodal Models are In-Context Learners✓ Link0.3640.5280.690Emu2 SDXL v1.02023-12-20
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation✓ Link0.3560.4940.721DreamBooth SD v1.52022-08-25
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models✓ Link0.3440.8330.413IP-Adapter-Plus ViT-H SDXL v1.02023-08-13
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing✓ Link0.2710.5470.495BLIP-Diffusion SD v1.52023-05-24
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion✓ Link0.2360.3780.624Textual Inversion SD v1.52022-08-02
Check out how to contribute new results.