Model

Here you define the base model you use for training and the output model you want to achieve.

Base Model: either provide the the path of a saved base model or provide a link to it. Set the Model type (SD1.5 to SDXL1.0) as well. Model Output destination: set any local folder with its name and type (ex C:/OneTrainer/Output/xxx.safetensors) Data Type: 3 options are available at the moment, float16, bfloat16 and float32. They all have different precision and will consume more or less memory.

Data Type Usage and values

Function	Fine Tune	LoRA	Embedding	Fine Tune VAE	Possible Values
Output	X	X	X	X	All
Weight	X	X	X	X	All
Overide Text Encoder	X	X	-	?	All
Overide Unet	X	X	-	?	All
Overide VAE	?	?	-	X	All

Note 1 : We need some more explaination on the data types.