Generates a resemblance of the character Druuna from the erotic comic series.
Trained on 127 images with 2,100 steps and the following resolutions ...
448, 512, 576, 640, 704, 768, 832, 896, 960, 1024, 1088, 1152, 1216, 1280, 1344
None of the example images were post processed or scaled.
Description
Comments (3)
if you could do alora of the comic that would be awesome
I'm always looking for more ideas and would love to give it a try but I don't know who it is, or what comic series. If you can give me more information I'll definitely take a wack at it.
@Tarterbox Not sure what comic he was thinking about, but here are three ideas I would love to see...
1. perchance image gen style lora; here is my favorite perchance image generator https://perchance.org/beta-zenitos-place-image-generator -- I get better images from that than I generally ever see in any local models I run... I'm pretty sure it is using a custom finetune of chroma behind the scenes (and chroma gets closer to that quality than any other model I've found).
2. prompt adherence lora; an all in one concept lora to expand on chroma's already impressive prompt following abilities -- an extensive library of poses, activities, actions, materials, physics, and a wide array of dynamic concepts.
3. background; a chroma version of the background lora for flux.1 dev -- it counters the typical image generator insistence on always using depth of field and distance fog/atmosphere, thus allowing potentially infinitely deep depths of field, so that both foregrounds and background can remain in crisp focus with clear visibility.