Recommended generating at 640x896.Trained at TF32 precision and saved as float. Still 128 dim size.Use AOM2Note: Feel free to see the metadata of my lora I included the full training cmdline if you wish to try and make it yourself.

Takamichi style and cover (no trigger words version)

Well it's really 1 Epoch but 27 repeats. Dataset used all Takamichi's Comic LO covers numbering 229.Trained on AOM2 hardcore as that was the most popular.This was a test train. But it turned out quite well. Edit: I guess civitai does not save file names when you upload it. The file was supposed to be called CoLOv5t_fp32.safetensors as shown in the example images.

CoLOv5t_fp32.safetensors

REAL V1 AOM2

Takamichi style and cover (no trigger words version)

Takamichi style and cover 

Recommended generating at 640x896.

Trained at TF32 precision and saved as float. Still 128 dim size.

Use AOM2

Note: Feel free to see the metadata of my lora I included the full training cmdline if you wish to try and make it yourself.

Files with SHA256: d141d342b3e9b5244c10d6b40e1b1248053a2ed2528c1aada78e8dd74f8cde86