BLIP-Diffusion SD v1.5

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Personalized Image GenerationonDreamBooth
Concept Preservation (CP)· 2023-05-24
0.547
best: 0.833 (IP-Adapter-Plus ViT-H SDXL v1.0)
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing arXiv:2305.14720
Personalized Image GenerationonDreamBooth
Overall (CP * PF)· 2023-05-24
0.271
best: 0.517 (DreamBooth LoRA SDXL v1.0)
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing arXiv:2305.14720
Personalized Image GenerationonDreamBooth
Prompt Following (PF)· 2023-05-24
0.495
best: 0.865 (DreamBooth LoRA SDXL v1.0)
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing arXiv:2305.14720