There are 2 versions of this Lora. 2nd version will be released soon.
Style Accurate isn't very flexible but it really captures the art style. Anime is more flexible but loses the original style.
Style Accurate - trained exclusively on screenshots from episode 1 and 2 - using the AnyLora checkpoint
Anime - trained with screenshots and fanart - using the Animefull-final-pruned-fp16
Full training details are in the "About this version" menu.
Like what I do? Please consider supporting me ☕ https://ko-fi.com/citronlegacy
Any amount would be awesome!
Description
Trained on: 71 images
Training Model: AnyLoRA_noVae_fp16-pruned
flip_aug: False
Num of Repeats: 10
Unit is Epochs or Steps: Epochs
Number of Epochs or Steps: 10
Training Batch Size: 2
Total Steps: 3550
Resolution: 512
Network Dim: Dim=32; Alpha=16
Lora Creation Process took: 0:37:25
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.