Download
1 variant available
fp16 SafeTensor
ChimeraMiXLv2_5-etc21-e20.safetensors
Half precision, best balance • 6.46 GB
Verified: 3 years ago
8510 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
(72)
Oct 25, 2023
Rebalanced, diluted a bit, hopefully mitigated the spots issue
Added some creative midjourney images to the training, did a native 20k fine-tune on a synthetic creativity reinforcement subset (135 images from chimera, dall-e3, midjourney)
Show more

5240 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
4.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

Initial version of Chimera XL, focusing on (un)realistic creatures, hybrids, monsters.
The training data had Gen1 pokemons (just their names, no type tagging), some LoL characters (Ashe, Akali, Ahri, Katarina, Star Guardian Jinx, Nidalee, etc), some OW characters (mercy, dva, black cat dva, tracer), species (tauren, navi, smurf, succubus, draenei, lamia, turian, asari, krogan, skrull), various wereanimals and hybrids, fantasy creatures (undead dragon, harpy, dryad, unicorn, centaur, humantaur, kobold, goblin, floran, avian, fairy, arachne, slime, griffin), regular animals, and various LUTs (see LUT Diffusion LoRA).
I used Dreamshaper Alpha2 as a base.
