Download
1 variant available
6340 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
1.6K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
3650 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
(104)
Jul 17, 2024
Trained with FP8 base instead of Full BF16 as it was trained on my laptop which can't handle more with just 8GB VRAM
I'll retrain it if necessary, once i'm at my desktop again
Show more

215.3K0 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
1.4M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M
3.9M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M

License:
CreativeML Open RAIL++-MLoRA is generated entirely from anime images.
-----------------------------------
Works well with Pony models.
Check samples for prompts :)
Note:
In case she gives you a headache with eyes: As with any other anime chars,
try adding wide-eyed to the negatives. Helps with small eyes.
-----------
2.5D Style: Previews generated with "score_9, score_8_up"
Anime-like: Use: "score_7_up, anime screencap"
-----------------------------------
Leave a like, comment, review but first of all, ENJOY ;)

