Download
1 variant available
fp16 SafeTensor
TanDo-style-LoRA_v1.0.safetensors
Half precision, best balance • 9.11 MB
Verified: 4 years ago
5130 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
00 1 2 3 4 5 6 7 8 9
(80)
Feb 23, 2023
Trained using AbyssOrangeMix2 model
23 images, handpicked, not cropped, added .txt captions (WD1.4)
10 repeats, 20 epochs, batch size 2
LR: 0.001, Unet LR: 0.001, Text encoder LR: 0.0005
Net dim: 8, Net alpha: 8
Runtime ~15min
Show more

25.2K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
419.5K0 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 9.0 1 2 3 4 5 6 7 8 9K
3.1M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M

Share your images here and leave a like if you enjoyed it! Get exclusive NSFW models at DeviantArt or Booth.pm.
LoRA based on the style of the artist Tando. Follow the artist and support if you like their work. No trigger word required. The end result depends on the base model used and the preferred weight. You can probably get a better adherence to the style by removing most if not all pony scoring/quality tags.
Recommended quality tags: score_9, score_8_up, score_7_up, score_6_up. Optional: source_anime
Recommended negative tags: score_4, score_5. Optional: 3d, lips
Recommended checkpoint: AutismMix_confetti
