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
Description
What this version does, is it takes almost all the layers and gives them to turbo 0.2 from Cornerstone, but the output project layers are given to Polyx's Distill.
Bottom right in 4 way grids
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.