Skip to main content
AIDiveForge AIDiveForge
🖼️

Diffusion Prompt Library

Image & Video · by AIDiveForge · Apr 17, 2026 · Beginner · ✓ 1 verified compat

Build a small, reproducible prompt set for a specified image model.

Get named prompt variants with assumptions and an evaluation sheet.

Download skill ZIP See the worked example

Free · 2 KB · SKILL.md, instructions and example files. Provide the target model, intended image and any reference assets; generation requires a compatible image tool.

A worked example

A small example to try before using your own data.

Input

{
  "brief": "A red ceramic mug on a plain cream background",
  "variants": [
    "front view",
    "three-quarter view"
  ],
  "model": "unspecified"
}

Expected result

Variant A: red ceramic mug, front view, centered, cream studio background, soft side lighting. Variant B: same brief with three-quarter view. Settings: unspecified until a target model is selected. Status: prompts proposed, images not generated.

What to check: 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.

Installation options and other formats

Install this skill

An agent skill starts with SKILL.md. The ZIP also includes its examples and any helper scripts. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Download SKILL.md 
python3 - <<'ADF_SKILL_INSTALL'
import hashlib, io, os, stat, tempfile, urllib.request, zipfile
from pathlib import Path, PurePosixPath
folder = "diffusion-prompt-library"
root = Path(os.environ.get('ADF_SKILL_ROOT', str(Path.home() / '.claude' / 'skills'))).expanduser()
destination = root / folder
if destination.exists() or destination.is_symlink():
    raise SystemExit('An installation already exists. Back it up and merge the ZIP deliberately.')
root.mkdir(parents=True, exist_ok=True)
request = urllib.request.Request("https://aidiveforge.com/skill/diffusion-prompt-library.zip", headers={'User-Agent': 'AIDiveForge-Resource-Installer/1.0 (+https://aidiveforge.com/skills/)'})
with urllib.request.urlopen(request, timeout=30) as response:
    data = response.read(8 * 1024 * 1024 + 1)
if len(data) > 8 * 1024 * 1024 or hashlib.sha256(data).hexdigest() != "bf821354559046dc600cc9f213793e310cf03e96e85d04e88fbcd6349e75d444":
    raise SystemExit('The download did not match this reviewed bundle. No files were installed.')
with zipfile.ZipFile(io.BytesIO(data)) as archive, tempfile.TemporaryDirectory(prefix='.adf-skill-', dir=root) as temporary:
    members = archive.infolist()
    if len(members) > 100 or sum(m.file_size for m in members) > 16 * 1024 * 1024:
        raise SystemExit('Unexpected archive size')
    for member in members:
        name = PurePosixPath(member.filename)
        if name.is_absolute() or '..' in name.parts or not name.parts or name.parts[0] != folder or '\\' in member.filename or stat.S_ISLNK(member.external_attr >> 16):
            raise SystemExit('Unsafe archive entry; nothing was installed')
        target = Path(temporary).joinpath(*name.parts)
        if member.is_dir():
            target.mkdir(parents=True, exist_ok=True)
        else:
            target.parent.mkdir(parents=True, exist_ok=True)
            with target.open('xb') as stream:
                stream.write(archive.read(member))
    staged = Path(temporary) / folder
    if not (staged / 'SKILL.md').is_file() or destination.exists() or destination.is_symlink():
        raise SystemExit('The skill could not be installed without replacing existing data')
    os.rename(staged, destination)
print('Installed the complete skill folder:', destination)
ADF_SKILL_INSTALL

Claude Code: ~/.claude/skills/diffusion-prompt-library/SKILL.md. Codex: ~/.codex/skills/diffusion-prompt-library/SKILL.md. Keep the complete ZIP folder when helper scripts are included.

🧠 Why it works

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

⚙️ How it works

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

Description

Get named prompt variants with assumptions and an evaluation sheet.

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

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

Recommended Use

Tools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.

Forge Auto-recommended matches

Tools
Workflow packs
Browse tools · Affiliate Disclosure · Privacy · Cookies · · Email Policy · Terms · DMCA