Hello!
When experimenting, I made a merge of Cornerstone Labs' Turbo Loras, and Polyx's Cosmos-Predict2.5-2B DMD2 LoRA
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.
How to use:
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 samplers
for schdulers, try beta57, beta, sgm uniform, and bong tangent, but simple and ddim uniform also work
Ignore:
Anima Turbo, Turbo lora anima, anima turbo lora, anima distil, anima dmd2, turbo anima, anima lora, turbo lora, fewer steps, turbo merge, distillation, anima distillation, accurate turbo, better turbo, improved turbo