3D Couple Enjoying a Piggyback Ride
Prompt
Render a joyful couple in polished feature-animation 3D, matching both reference identities, facial structures, expressions, and proportions consistently. In a sunny daytime park, a man in a black baseball cap, bright-orange drawstring hoodie with front pocket, black cargo trousers, and black-and-red high-top sneakers gives a laughing woman a piggyback ride. She wears an orange cap, matching orange hoodie, black cargo trousers, and the same black-and-red sneaker palette. Let her wavy hair stream behind as her arms wrap his shoulders and he supports her legs. Center the full piggyback action in a vertical 4:5 frame with comfortable headroom. Show the man from above the knees and keep the woman’s feet completely visible. Surround them with green grass, rounded stylized leafy trees, and a cloudless blue sky, softening only the distance with depth of field. Use bright neutral midday daylight, even exposure, minimal soft shadow, clean vibrant daytime color, smooth 3D shading, global illumination, high-resolution surfaces, and 4K quality. Exclude golden-hour or sunset light, clouds, fog, dark exposure, and any crop of feet or legs.
How to use this prompt
Paste the complete prompt into Gemini. Add any required reference image, generate the first version without rewriting the source prompt, and then request one precise revision at a time.
Best AI model
Gemini is the model identified by the original source page for this prompt.
Tips for better results
• Attach a clear, well-lit reference image and state which identity details must remain unchanged.
• Keep the requested 4:5 framing during revisions.
• Preserve the specified lighting direction and contrast before changing wardrobe, pose, or background.
• Generate the complete prompt first, then refine one visual detail per revision.
• Keep the core subject and composition consistent while comparing variations.
Frequently Asked Questions
What does “Joyful Piggyback” create?
It creates the subject, composition, and visual treatment described in the original prompt.
Which model should I use?
The source identifies Gemini; follow the prompt's own model and reference-image requirements.
Can I customize the result?
Yes. Generate the original prompt first, then change one detail at a time while preserving the core composition.

