If you enjoy my work please leave a like or a review. Pics Vids of your work are also appreciated :)
Description
FAQ
Comments (10)
Quite Fitting as her face is somewhat AI generated effects.
Hell, even I'm AI generated. I couldn't hel-
snaps out of it
phew, my soul almost got taken over by openai
Great lora! Would you be able to include your config or dataset for the training? I'm having trouble training a good lora.
I dont share most of datasets as I dont own any of the images
@JaneB willing to share #of images, epochs, and what tool you used for training?
@superpooper I use ~25 images for all the hunyuan loras and trained on diffusion-pipe. Steps: 4,375
Epochs: 35
@JaneB thank you so much, I use about the same images for 1200 steps, maybe this is why my Loras are unusable. I'm going to try matching closer to what you're doing
@superpooper try increasing the learning rate a bit too
@JaneB any recommendations? The learning rates are a bit tricky for me to understand
@superpooper I think the default is 0.0002 (might be another zero there so verify that) I do 0.0005
@JaneB I've tried .0005 LR with 1800 steps, I think I may have over fit it now, but it worked for me. Thank you for sharing (: