This mix is ​​a strange combination of turbo and style loras. Its goal is to quickly generate images with VERY limited resources. I don't really understand what I'm doing, since i'm experimenting and constantly testing things.
The models in INT8 (row_wise) for those who can't upgrade CUDA for convrot acceleration.
I hope you will find this mix useful.


Versions
T1 - Imagine throwing a bunch of LoRAs into a blender and mixing together several checkpoints—that’s exactly what this is. I don’t even remember exactly what’s in there.
T2 - So i saved list of loras that i like and mixed weights, based on Anima 2.9b (sadly this model is slower due to extended blocks and knowledge).
T3 - I discovered SVD merging not just lora stacking and saving model and picked the same loras as in T2, and the AnimaYume 1.5 came out so it's based on this version.
T4 - I decided to start from scratch, reviewed loras, ditched old ones and merged with SVD with higher rank, i don't know what else i can do, so this version might be final if i don't find something interesting again.
T5 - Some guy on huggingface released so called "Anima Lighting" version, so i tried it at 4 steps and it's very good, so this version is based on Lighting.

Usage
Minimal steps is 6, but 8-12 obviously better.
CFG-1 - as for all Turbo loras and models.
Sampler - Euler (too chaotic for my taste) or ER_SDE (stable), recently i liked Res Multistep.
Sheduler - Simple or Beta57.
I haven't tested high resolutions because I'm used to generating at 1024 because it's faster and prefer inpainting or Face Detailer over upscaling and Hires.fix.