Textual Inversion SD v1.5

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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)· 2022-08-02
0.378
best: 0.833 (IP-Adapter-Plus ViT-H SDXL v1.0)
SOTA
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion arXiv:2208.01618
Personalized Image GenerationonDreamBooth
Overall (CP * PF)· 2022-08-02
0.236
best: 0.517 (DreamBooth LoRA SDXL v1.0)
SOTA
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion arXiv:2208.01618
Personalized Image GenerationonDreamBooth
Prompt Following (PF)· 2022-08-02
0.624
best: 0.865 (DreamBooth LoRA SDXL v1.0)
SOTA
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion arXiv:2208.01618