


Image · GPT Image 2.5
Two-Scene Retro Travel Poster
Design the user-provided location or theme as a 4:5 vertical travel poster: the upper half presents a realistic scene, and the lower half converts the same scene into a hand-painted watercolor and gouache illustration.
Prompt
Create a premium FULL-FRAME 4:5 vertical photo-to-illustration travel poster for [COUNTRY / CITY / LOCATION / SUBJECT].
TEXT-TO-IMAGE ONLY — generate everything from the written subject alone. No reference image required.
CORE CONCEPT:
Create a charming vintage travel-journal poster with a precise horizontal split: the upper 50% features a realistic photographic scene, while the lower 50% transforms the SAME scene into a beautiful hand-painted travel illustration.
COMPOSITION:
Keep the main subject consistent across both halves. The upper section features natural lighting, authentic textures, and realistic details. The lower section reimagines the scene using simplified shapes, soft watercolor and gouache, and a warm cream paper background.
STYLE:
Retro travel postcards, hand-painted architecture, delicate botanical details, playful handwritten lettering, tiny stars and hearts, and subtle paper texture. Add a short, creative English headline and a small destination label inspired by the scene.
COLORS:
Warm ivory, sky blue, muted teal, sunny yellow, coral, sage green, and terracotta. Use cheerful, harmonious colors with a nostalgic afternoon atmosphere.
FINAL AESTHETIC:
Real photography × illustrated travel memory × vintage editorial design × playful handwritten typography.
AVOID:
Combining unrelated scenes, changing the main subject between halves, clutter, excessive text, glossy digital art, 3D, logos, watermarks, and mockups.
FORMAT:
Exact 4:5 vertical ratio, full-bleed artwork, complete canvas coverage, clean 50/50 horizontal split, high resolution.
How to use
Usage tips: replace [COUNTRY / CITY / LOCATION / SUBJECT] with a specific travel destination or theme, then enter it into an image generation tool; suitable for making destination posters, travel memory visuals or social media covers, and check whether generated text needs post-production typesetting.
Details
- Type
- Image
- Model
- GPT Image 2.5
- Source
- Saul Goodman
- License
- Source-author-rights
- Published






