
2x2 grid, do this for shahnameh and non-copyrighted public space books: WITH input(work) AS ( VALUES (:WORK) ), spec AS ( SELECT title(work) tt, iconic_figure(work) fg, integration_mode(work) md, negative_lines(work) ng, caption(work) cp FROM input ), mark AS ( SELECT fuse(fg, tt, md) AS m FROM spec ) SELECT emblem_render( m, carve_negatives(m, ng), ink=>'black', ground=>'neutral', caption=>serif_caps(cp) ) AS epic_emblem FROM spec, mark -- E₁: CHECK ( integration mode applied AND connected(S ∪ W) = 1 ) -- E₂: CHECK ( figure iconic of work AND heraldic pose ) -- E₃: CHECK ( binary ink AND negative lines interior ) -- E₄: CHECK ( word legible AND silhouette coherent ) -- E₅: CHECK ( serif caps caption AND neutral ground ) -- forbidden rows (word beside figure / generic figure / gray / illegible / no caption) violate CHECKs ;
This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2.5 using: 1672:941 · Historical · Poster · Mythology. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.