align_sd

align_sd copied to clipboard

About the training data and time cost of lora fine-tuning

3

Thanks for your great work! I wonder how much time it costs to train the Lora on the dataset (1M DiffusionDB + subset of Laion5B) on, for example, 4 GPUs?

cjfcsjt

when will hps classifier training code be released?

3

Thank you, I have successfully replicated the training of LoRA according to your code, and it does improve the performance of Stable Diffusion significantly. May I ask when the training...

huxian0402

Regarding the validity of the Human Preference Classifier

1

Hi @tgxs002 , thanks for your work, and making the dataset and classifier open-sourced! As a sanity check, I evaluated your trained HPC on the examples in the training data...

Hritikbansal