Download
1 variant available
fp16 SafeTensor
ADAWONGv11_Lora32.safetensors
Half precision, best balance • 17.69 MB
Verified: 3 years ago
4,5300 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3040 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
460 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Mar 13, 2023
Trained to do both NSFW or SFW in prompts/negative prompt
Use: ((sfw)) and ((nsfw))
113 picture dataset
2 repeats/ 2 concept folders
0.00016 lr = unet lr
0.00003 text lr
dimm 128 (resized to 32)
Show more

2.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
2.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

recommended weight: 0.7-1 or 1.25 if you want some more distinct character generation with some overfitting
>> HiResfix <<
CLIP 2
Tips:
use "leather top" in negative prompt to remove it from image gen
put lora identifier in front of trigger word:<lora:ADAWONGv11_Lora32:0.7> ADAWONG
if you would like to support me or requests:
https://ko-fi.com/s6yx0
