character-design-sheet

Create consistent characters across multiple AI-generated images via inference.sh CLI. Requires inference.sh CLI ( belt ). Install instructions AI image generation produces different-looking characters every time, even with the same prompt. This is the #1 challenge in AI art for any project requiring the same character across multiple images. Shows the character from multiple angles: Shows the character's face with different emotions: Minimum 6 expressions: neutral, happy, angry, sad, surprised, thinking. Multiple outfits for the same character: Document exact colors for consistency: The most practical consistency technique: write a 50+ word detailed description and reuse it exactly in every prompt. Use this exact block in EVERY prompt for this character, only changing the action/pose/scene. Include proportion style in your prompts: "realistic proportions" vs "anime style proportions" vs "chibi proportions" For projects requiring many images of the same character, train a LoRA: LoRA Training Tips: For ongoing projects, maintain a character bible document: Browse all apps: belt app list - Need 10-20 reference images of the character (consistent style) - Train on specific trigger word (e.g., "maya_chen") - Scale 0.7-0.9 balances consistency with prompt flexibility - Lower scale = more creative freedom, higher = more strict matching