domains / families / media / scenario-model-training

scenario-model-training

separate

Use when generated assets must keep a consistent style, character, or product look and references stop scaling, or when a user asks to train a custom model through the Scenario MCP, fine-tune a LoRA, clone a voice, curate a training dataset, choose a base model, set epochs and sample prompts, estimate training cost, diagnose a trained model that lost its identity or has one epoch, or generate with a trained model. Keywords: custom model, LoRA, dataset curation, epoch previews.

When to use

• train a custom model
• fine-tune a LoRA
• clone a voice
• curate a training dataset
• choose a base model
• set epochs and sample prompts
• estimate training cost
• diagnose a trained model

When not to use

• cheaper first steps like prompts, references, and control maps

Skill page

Source