Image prompt skeleton
A fill-in structure for image models that keeps subject, environment, light, lens and style in the order the models weight them.
{{subject}}, {{action_or_pose}}, in {{environment}}, {{lighting}}, shot on {{lens}}, {{style}}, {{mood}}
--- parameters ---
Aspect ratio: {{aspect}}
Seed: {{seed}}
Negative: {{negative}}Fill these in
| Placeholder | What goes here | Example |
|---|---|---|
| {{subject}} | Subject | a weathered brass compass |
| {{action_or_pose}} | Action or pose | resting open on a folded map |
| {{environment}} | Environment | a cluttered ship cabin |
| {{lighting}} | Lighting | low afternoon light through a porthole |
| {{lens}} | Lens | 50mm, shallow depth of field |
| {{style}} | Style | documentary photography |
| {{mood}} | Mood | quiet, unstaged |
| {{aspect}} | Aspect ratio | 3:2 |
| {{seed}} | Seed | leave empty for random |
| {{negative}} | Negative prompt | text, watermark, extra fingers |
Notes from the author
On Midjourney, put the parameter block after --ar and --no rather than as text. On Stable Diffusion the negative goes in its own field. Record the seed if you want the image back - it is the only part of an image prompt that is genuinely reproducible.
Tagged