Character consistency in AI image generation — where prompts break down and LoRA helps

📦 Training template: github.com/sm1ck/honeychat/tree/main/tutorial/03-lora — a generic Kohya SDXL config with placeholders and a dataset curation guide. No docker-compose (LoRA training is GPU-heavy) — you bring your own GPU or rent one. Here's a failure mode many AI companion apps run into on launch day: users send two requests in a row for the same character, get two different faces, and conclude the product is broken. They're not wrong to feel that way. Character identity is part of the prod