Hello!When experimenting, I made a merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/2560840/anima-turbo-lora">Cornerstone Labs' Turbo Loras</a>, and <a target="_blank" rel="ugc" href="https://civarchive.com/models/2466415/cosmos-predict25-2b-base-distilled-extracted-dmd2-lora">Polyx's Cosmos-Predict2.5-2B DMD2 LoRA</a>Because one is rank32 and one is rank64, I did a binary masking with various routing maps. The version section describes what each one is. I think DMD2 Output Projection is the best for my taste. Works across various styles. Please post your images and feedback, I would like to hear if this helped you.<h3 id="how-to-use:"> How to use:</h3>I suggest between 6 and 12 steps. If you lower the weight below 0.8 or so, you might want extra steps (trial and error)er_sde and euler are good samplersfor schdulers, try beta57, beta, sgm uniform, and bong tangent, but simple and ddim uniform also work

Expressive Accurate Turbo for Anima

For this version, I compared turbo 0.1, turbo 0.2, and the dmd2 distill to their own averages, as a ratio, and took the layers that were furthest from each lora's average. This was to help compensate for the rank32 vs rank64 difference.

Files with SHA256: b486fcdbdb4fac3a568fe6e3cc083ec9fae63b720ad2a4e70dcd4b240d2d1ba2