Support me: https://ko-fi.com/elevatedone ☕
Please post suggestions for future models here: https://civitai.com/articles/5921/suggestion-list
The early access can be removed (for everyone) by donating to my Ko-Fi (say the model name in the message field).
I somehow overcame my thoughts of trying to save money and not doing stuff and started training more checkpoints. If you like the models that I put out, please support me on Ko-Fi, since it costs me between 5-10$ to train a checkpoint.
Information:
The model is based on Dark Sushi Mix (2.25D) by @Aitasai
Base model for training used was T-ponynai3 v5.5 by @Tonade
The model was trained at 1024x1024 resolution
The model was trained with around 500 pictures and around 3000 steps after batch size of 12 I believe. (I don't have the config anymore as I deleted the server I ran it on, since it ate $0.5/h, which is a lot)
If you want to check the other retrains of mine, here you go:
flat2DAnimerge (Original by @bigbeanboiler) (LoRA version)
Flat2D (Original by @bigbeanboiler) (Checkpoint version)
Animeliner (Original by @Goofy_Ai) (LoRA version)
Animeliner (Original by @Goofy_Ai) (Checkpoint version)
SD15Lorium (LoRA trained on data from 34 checkpoints, with triggers for all of them. It's kinda bad since it was trained with rank of 16 I believe)
YOZORA (Original by @YozoRaAru) (Checkpoint)