search

tencent-ailab / IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Apache License 2.0
5.18k stars 335 forks source link

Details on quantitative results #432

Open HoiM opened 2 weeks ago

HoiM commented 2 weeks ago

Thank you for your work. When calculating CLIP-I and CLIP-T, did you use text prompt as an input into the model? Is the image prompt the only input?

xiaohu2015 commented 2 weeks ago

coco dataset have text captions

HoiM commented 2 weeks ago

coco dataset have text captions

I know it has captions. What I plan to do is to conduct same evaluation with my own IP-Adapter.

I don't know if I should use text prompt when the model generates image samples.