Next version will be done by Gemini 3. I have manually did 195 images already which took many hours. I just need to train.
This was done with learning rate 0.00007
The reason why I chose this was double-0-seven (007), but with double 0's. It turned out great but I didn't use masking. I learned many things from Gemini 3. This lora took 2 days to train.
Onetrainer:
training resolution: 1328x1328
rank: 16
images: 195
model: float 8bit (w)
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)
R1.5
Training captions;
overexposed (Comment: Lighting), fishnet lingerie, metallic choker, dragon wings, digital 3d render, large breasts, wearing clothing, ear jewlery (Comment: fuck... its spelt wrong), o-ring collar, arm accessories, smile, angry, very happy, g-string underwear, body chain, bikini, seductive smile, shy, annoyed, grin, big smile, worried, silly face, yawn, sad, exhausted, bikini top, loin cloth, rear loin cloth, v-neck dress, wearing armour and clothing, flower dress, black hoodie, magazine cover, meme format.......Many more, I didn't caption any of the dragon's color.
This lora suffers the same fate as illustrious, it just can't get her likeness correct every generation, mostly her hands, tail, ears, feet.
Description
AIToolKit
Qwen2512
Trained resolution 1536
Rank 128
images 262 (Mostly 4K images)
adamw8bit
learning rate 0.0001
PyTorch offload (Text Encoder slider set to 0%)
time 9 hours and 17 seconds (I'm surprised it didn't crash)
vinci19 is the trigger word, however since I used person as a class it doesn't work as intended and needs anthropomorphic to work.
Use higher strength like 1.2 for better likeness. This is undertrained and works well with higher strength.
Manually captioned, this lora has the same problems as illustrious. There is no way it's my captions because it corrects itself RNG style.
1.5 Because it does improve resolution but is lacking hand and feet.
This lora is really fixated on 3D since I tagged it, you can put it in the negative.