A request of @DCl.
Jessica Cediel is a Colombian tv host, journalist and actress.
1000-step TI trained on a dataset of 20 images with my usual settings.
Curious about my work process? I have summarized it here.
Appreciate my work? My TIs are free, but you can always buy me a coffee. :)
Description
1000-step TI trained on a dataset of 20 images with my usual settings.
FAQ
Comments (2)
Love it! Would love to see some of the BlackPink girls. I can never get the Loras to work right. I have done most of the steps for you already. You have the magic touch. This is Lalisa of black pink. Huge star. https://drive.google.com/drive/folders/1wslCDR3Fg_iUS7nTLg2Ylrxi6o8uYFVM?usp=sharing
Big fan of your work, Jernau. I'm curious. Have you noticed whether higher token counts require more training steps? Does a higher token count give an embedding more "resistance" to being washed out by styles or an over-trained checkpoint? Is there a drawback to a 1 token TI vs a 7 token, for example?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.