Quick Question: what is the actual training dataset volume?

[bsun0802]

Hi Author,

Thanks for the great work. I've been curious in the "ID-Oriented Human Data Construction" described in paper, after ID verification and other filtering, what is the final training dataset volume?

I'm curious about how many training data, will empower the ID-preservation for a diffusion model, e.g., 10k, 100k, or 1M, etc. Would love to see an ablation for how the model progress when fed with different magnitude of data size.

Thanks!

[Paper99]

Hi, for the model reported in the paper, we used filtered 110K images to train. No in-depth exploration of changes in the scale of training datasets.