Hi! This is my unofficial Anima Turbo v1.0 LoRA. I made this so I could use it in my own merges. It also looks good on its own.
This LoRA was extracted from the new Anima Turbo v1.0 base model
Not much to say about this one. Good for merges, or if you dont want to use the base model and still get the Turbo v1.0 style and speed.
CFG: 1.0
Steps: 8-12
Strength: ~1.0
v1.0-Resize/DoRA
This is more of a technical update. I pulled a fixed 64 rank with dora. Then resized using budgeting/svd 8-64. Result? Quality improves, overall better balance/health, file size is nearly half the original 64 and just over the original 32. If you dont want the DoRA, strip/convert the keys before merging or exclude them during.
v1
Original extract with multiple variants 32 / 48 / 64
I do this for fun and to learn. Likes, comments and reactions are nice to see if my efforts are worth while and posting. I dont really care about the buzz or whatever but drop me a comment and like if you enjoy what Ive done. <3
Description
This is more of a technical update. I pulled a fixed 64 rank with dora. Then resized using budgeting/svd 8-64. Result? Quality improves, overall better balance/health, file size is nearly half the original 64 and just over the original 32. If you dont want the DoRA, strip the keys before merging or exclude them during.
FAQ
Comments (3)
Works really well on anime style renderings - if you're trying 3d/painterly/real images probably best to avoid. Overall, would recommend for the anime or western styles, it also brings a good bit of stability.
What tools do you use to extract loras from finetunes?
I use my own :) LoRA Training Tools. Ive been working on it as I learn. I started it to help make character loras and been adding more tools to it as I progress. Currently I use it for everything that I do and post here.