haoosz / ViCo

Official PyTorch codes for the paper: "ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation"
MIT License
238 stars 15 forks source link

reference image on evaluation? #13

Open DJLee68 opened 1 year ago

DJLee68 commented 1 year ago

Hello!

image

On paper's quantitative comparison, what did you use reference image for each sample and prompt? Was it sampled from training images for each prompt or fixed?

And also, which checkpoints(300, 350, 400?) did you use for quantitative comparison?

Thanks in advance!