This is my first public lora which is generated on a RTX 5090 with 1080x1920 resolution. I figured out that using a higher image resolution then training on a lower resolution, helps image quality. The detail of the skin is WOAH. Also, I just realized that image artifacts/compression affects the quality HUGE, dramatically huge. Hope this info helps.
V0.5 (Recommended)
prompt: dragon, female, red scales
V0.6b (Testing Phase, more stable???)
Using Vinci194 in the prompt isn't necessary
prompt: female, red and black scales, orange hair, long snout
Options Version (75 Images x 10 repeats)
V0.5 & V0.6b
(78 images x 10 repeats)
Prodigy is king
Basically default settings prodigy with cosine
bfloat 16 for training data type
Lora rank 128
Recommended Model (https://civarchive.com/models/97479?modelVersionId=1323509)
model base (https://civarchive.com/models/1369089?modelVersionId=1546777)
Around 1500 to 6200 steps
Original Creator: https://x.com/vinci194 (Vinci194)
3D Model by: FoxiPaws
Follow the original creator if you enjoy this lora.
They have NSFW in their patreon page here (https://www.patreon.com/VinciTheDragon)
Description
V0.6b
Added Vinci194 to the trigger prompt, this is the only caption used in all the 78 images
Might be ever so slightly better than V0.5. I'd still use V0.5 just to be safe, more testing is needed
Might add more options
another 10 or so hours of gen time, 8 hours of pain from testing, I don't care anymore, here you go