# GPT-5 Image Gen Prompt Template Example.
Capture a scene with **[subject(s)]** over **[location and environment]**. **[brief narrative beat or moment to capture]**. In a style of **[art/style family]** rendered in **[pipeline/medium]**, with **[hallmark style traits]**.
## Non-negotiables
<series_constants>
<Character bible>
- **[Character A]** — [build/skin/face markers/hair/defining feature(s)].
</Character bible>
<Environment>
- [Architecture/terrain/props/ambient particles]; [foreground/mid/background anchors]; [signature element(s) present but not dominant].
</Environment>
<Camera & composition>
- [Lens/focal length], [camera height/angle], [framing rule], [depth of field focus target], [motion or stillness cues].
</Camera & composition>
<Consistency locks>
- Faces, hair, outfits, palette, environment architecture, and lighting must match the above exactly.
</Consistency locks>
</series_constants>
## Output & conduct
- Output: exactly **1 image**, aspect ratio **[e.g., 1:1]** at **[target px, e.g., 1024×1024]**.
- **No** text overlays, watermarks, borders, captions, or extra panels.
- If any detail is ambiguous, **do not ask questions** — choose the most reasonable assumption that preserves every Non-negotiable.
- Resolve conflicts by prioritizing: **Non-negotiables → everything else**. Avoid adding unspecific elements.
Created
August 12, 2025 14:00
-
-
Save ditpoo/021cf55abb9c927dbe0042c546f96a99 to your computer and use it in GitHub Desktop.
GPT-5 Image Gen Prompt Template Example.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment