Skip to content
Search
FRAME 0289

Colosseum travel poster — composed GIF

9 frames, 2 seconds, 360×480px; repeats indefinitely. GPT Image 2.6 frame-sheet + local GIF encoding.

Generated with GPT Image 2.6Generation prompt language · English · Run recorded Nov 9, 2026 · Updated Nov 20, 2026No reference image · 0 reference images used
  • Output 1 · 360 × 480 · image/gifGIF generated with GPT Image 2.6 · 9 frames · 2 s · Loops continuously

Use the complete adapted prompt without a reference image.

Colosseum travel poster
GIF generated with GPT Image 2.6360 × 480Full-size image
Prompt · English
A living mid-century gouache travel-poster painting of the Roman Colosseum, locked-off static camera, a seamless looping animation. The ruined amphitheater sits low in the frame in sun-bleached ochre, sand and travertine with dusty rose and pale blue-grey arches, painted in dry-brush gouache with flaky, speckled edges and worn-away patches. A tall Italian stone pine in dark green and bottle-green leans in from the right, a vintage teal street lamp on the left, rose-coral flowering shrubs at the base. Open warm cream paper-textured sky fills the upper two thirds with fine paper grain. Gentle motion only: a few tiny birds drift across the sky, a cyclist rides slowly along the piazza, a small scooter, a couple in coral and mustard strolling, pine foliage barely sways. Soft warm afternoon light, long pale shadows, flat matte shapes, vertical 3:4, perfect loop. Production adaptation: The text above defines the visual idea and action. For this call output only ONE PNG SPRITE SHEET, NOT a GIF file: exactly 4 columns by 2 rows, 8 equal portrait 3:4 cells, chronological row-major order. No border, grid lines, gutters, frame numbers, timestamps, or extra text. Fixed camera and ground line unless the action explicitly moves the camera. Keep scale, character identity, palette and geometry consistent; each cell is one distinctly different consecutive animation pose with nothing crossing cell boundaries. Cells will be extracted and encoded locally afterward. Make the motion return naturally from the final cell to the first.
1,536 characters

How to use

Use the complete adapted prompt without a reference image.

Reuse the archived GPT Image 2.6 sheet and resample its action to nine frames. Sources with eight poses split one held pose across two encoded frames without adding a new pose; longer sequences select nine chronological poses. Preserve total duration and loop settings. Small source cells are enlarged for display without adding detail. The GIF is composed locally; the image tool returned a still PNG. The source sheet, exact crops, frame delays and first-frame poster are retained in the campaign archive.

Result and limitations

9 frames, 2 seconds, 360×480px; repeats indefinitely. GPT Image 2.6 frame-sheet + local GIF encoding.

Reviewed all nine-frame sequences in four contact sheets: action order, identity, captions and final poses retained. This output reuses archived GPT Image 2.6 source pixels; no new provider call. One held pose is split into two frames; eight distinct source poses, nine encoded frames. Total duration and playback count preserved. Original source review (frame counts describe source only): Eight drawn gouache city frames show cyclists, scooter, people and birds moving against a recognizable Colosseum. Actual 3:4 center crop and 2-second repeating playback. Visible position reset at loop boundary and minor architectural redraw drift mean this is a stylized keyframe adaptation, not the seamless original-prompt target.

Source

Adapted by Prompt Seen from @devteamdrew's original prompt. The author labels the source work Image 2.6. This adaptation uses GPT Image 2.6. The tool returned no exact API model ID. The prompt preserves its submitted language on both page editions. Likes describe the whole source post, shared by variants, and are not engagement for this example.

Variants from the same source post: Golden Gate gouache waves · Mount Fuji travel poster

Test prints

0289-A · Displayed run

Model
GPT Image 2.6
Recorded
Nov 9, 2026
Provider
OpenAI + local GIF encoding

What we saw: Reviewed all nine-frame sequences in four contact sheets: action order, identity, captions and final poses retained. This output reuses archived GPT Image source pixels; no new provider call. One held pose is split into two frames; eight distinct source poses, nine encoded frames. Total duration and playback count preserved. Original source review (frame counts describe source only): Eight drawn gouache city frames show cyclists, scooter, people and birds moving against a recognizable Colosseum. Actual 3:4 center crop and 2-second repeating playback. Visible position reset at loop boundary and minor architectural redraw drift mean this is a stylized keyframe adaptation, not the seamless original-prompt target.

Output
  • Colosseum travel posterGIF generated with GPT Image 2.6

Source and licence

Site text licence (CC BY 4.0) · Testing method

Colosseum travel poster
Creator: Prompt SeenAI-generated demonstration · Prompt SeenLicence: CC BY 4.0Generated image

Inspiration & source evidence

This prompt is an independent adaptation. The image shown here is our own recorded result.

Original content
X · devteamdrew
Source snapshot
Whole original post; shared across variants, not this adaptationSource post likes: 557Observed 2026-11-07
Evidence
Archived public X snapshot and complete author promptIndependent adaptation; full original preserved separately

These figures belong to the original post or video. They are dated snapshots, not live counters or ratings of our image.