Ahh, Anima, my favorite model for fun and fanarting around. I love this model. Klein 9 is my favorite trusty working companion, but Anima is my favorite recreational model. Even simple prompts get great results, and there's no need for quality tags and all that other nonsense. Just describe the image, and it'll do it. Samples are done with the model alone, no LoRAs or anything, just a few descriptive words.
The official turbo LoRA dropped, so I'm sharing the new version of the merge I'm using. This one does best at 8 steps. Full checkpoint, no text encoder or VAE needed, and it's small and fast. The results look way nicer to me than what my v1 was putting out, so yeah. Keeping this version.
This is a merge of the fp8 diffusion model of Anima Base, the new official turbo LoRA by the very people who gave us Anima (yay), the Heretic-Abliterated version of the Qwen text encoder (so you can prompt for pairs of small blue birds without being censored for it), and of course the standard VAE.
Stick it in a checkpoint loader, set it for CFG ~1-1.3 (yes, its negative prompting ability survives, I use CFG 1.3 all the time) and 8 steps or so, and have fun.
I also like some of the outputs I get at 4 steps, but then maybe that's just me. You'd probably find them too washed-out. 8 steps is pretty good.
