Model

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

• Hugging Face Token: you can specify here your HF token, required to download gated models from Hugging Face (SD3, Flux). It will be saved locally in secrets.json and reused when loading any preset.
• Base Model (default: Hugging Face link): either keep the default or provide the path to a saved model (in safetensor format or a directory for diffused models).
• Vae Override (default: blank): If you want to use a custom VAE, provide a Hugging Face link or a path to a local file.
• Model Output destination: default models/lora.safetensors, you can set any other local folder.
• Output Format (default: safetensors): Here you can choose between the default safetensors and the optional checkpoint format.
• Data Type: several options are available. The default presets (#SD1.5 LoRA, #SD1.5 Embedding, ...) will set up defaults values, you can stick to it, they are working.