---
name: "diffusion-prompt-library"
description: "Build a small, reproducible prompt set for a specified image model. Use when the user needs: Get named prompt variants with assumptions and an evaluation sheet."
license: "CC-BY-SA-4.0"
metadata: {"version": "2026-10-17.1", "category": "image-video", "publisher": "AIDiveForge"}
---

# Diffusion Prompt Library

Get named prompt variants with assumptions and an evaluation sheet.

## Requirements

Provide the target model, intended image and any reference assets; generation requires a compatible image tool.

## Workflow

1. Record the exact model and supported controls. Do not prescribe a sampler or CFG value for a model that does not expose it.
2. Separate subject, composition, lighting, style and excluded elements. Keep reference rights and required brand constraints explicit.
3. Change one dimension per variant and keep the remaining controls fixed where the tool allows it.
4. Store the prompt, seed/settings when available, and actual output identifier together.
5. Evaluate the generated outputs against the requested subject and composition; label unrun variants as proposals.

## Worked example

Read `examples/input.txt` and `examples/expected.txt` before adapting the workflow.

## Acceptance checks

Change only view angle; do not fabricate seeds, sampler support or generated results.

## Limits

This is a prompt/evaluation workflow, not a pretested library of model-specific settings.

Worked example included. Model-specific performance and vendor compatibility have not been benchmarked.