Trained from Kincora's work, based on PonyXL v6.
V02, re-did captions, smaller dim.
Yay~ kinda overwrote the base model's style completely, it's a small win (ﾉ◕ヮ◕)ﾉ*:･ﾟ✧
Description
FAQ
Comments (5)
Can you make it smaller?
"Regarding LoRA file size:
A higher DIM results in a bigger size.
Training with a lower DIM (for example 32) takes slightly less amount of time but gets worse in learning artist style. If you need to reduce LoRA size, try "remake dimension" using extension SuperMerge.
Here is comparison of:
1. anmiXL_V1 (870MB)
2. anmiXL_V1 remake dimension to DIM32 (217MB)
3. Same dataset trained with DIM32 natively (217MB)
https://civitai.com/posts/1379092
I personally feel "remake dimension" is better than training with DIM32 natively.
Hide"
-----By silvermoong
I can make it smaller, easy peasy, but on pony model, smaller is a risk 😂
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.