Capybara Tower Selfie, made with GPT Image 2.5 Sunburst
Example made with GPT Image 2.5 Sunburst

Text to imageAnimals

GPT Image 2.5 Sunburst animal photo promptCapybara Tower Selfie

The exact text-to-image prompt behind this picture, made with GPT Image 2.5 Sunburst.

Prompt

Wide 16:9 landscape frame. Three capybaras cluster shoulder to shoulder on a Paris lawn as though posing for a cheerful selfie, one curious, one sleepy and one looking slightly away, with the Eiffel Tower softly visible behind them. Keep their full heads and front paws naturally proportioned. Warm evening sunlight, playful 28mm wildlife photography, cream stone and fresh green surroundings, deadpan holiday charm, no text.

Prompts are kept in their original English to help reproduce the example. Copy one as it is, or adapt it for your project.

Opens GPT Image 2.5 Sunburst with this prompt and the settings below filled in.

135 tested GPT Image prompts →

Settings

Mode
Text to image
Aspect ratio
16:9
Quality
high
Price
From 2 credits

The exact price shows before you generate.

Make your own version

  1. For a different mood, rewrite only the light: Warm evening sunlight.
  2. playful 28mm wildlife photography sets the whole feel of the shot. Swap it for another camera style to change the vibe.
  3. The prompt ends with no text. Leave that in, or the model may add random lettering.

Where this idea comes from

Inspired by an idea from @berryxia_ai, collected in jamez-bondos/awesome-gpt4o-images under CC BY 4.0. PopNow wrote this prompt and made the example above.

Scene prompt guide

How the scene is composed

Three capybaras crowd together on a Paris lawn for a holiday selfie, with the Eiffel Tower soft in the background and warm evening light over everything. It works because each animal gets its own mood, the framing is clearly stated, and the prompt closes with a style and a ban on text.

  1. Subject and stagingThree capybaras cluster shoulder to shoulder on a Paris lawn as though posing for a cheerful selfie

    This sets the count, the grouping and the selfie idea in one line. Remove 'shoulder to shoulder' and the animals may spread out, so the selfie feeling is lost.

  2. Individual expressionsone curious, one sleepy and one looking slightly away

    Giving each animal a different mood stops the model from cloning one face three times. Without it you get three identical stares and the scene loses its humor.

  3. Landmark backgroundwith the Eiffel Tower softly visible behind them

    This places the scene in Paris without letting the tower take over. 'Softly' keeps it slightly blurred so the capybaras stay the focus; delete it and the tower may compete for attention.

  4. Anatomy guardKeep their full heads and front paws naturally proportioned.

    Group animal shots often crop heads or warp paws. This line asks the model to keep every head and front paw whole and in scale, which matters most in a tight cluster.

  5. Light, style, paletteWarm evening sunlight, playful 28mm wildlife photography, cream stone and fresh green surroundings, deadpan holiday charm, no text.

    This sets golden light, a wide-angle wildlife look, a limited color palette and a dry comic tone. 'No text' keeps signs and captions out. Drop it and stray lettering may appear.

Camera and light

The look depends on a wide lens, low warm light and a clear distance between the animals and the tower.

Camera
A selfie suggests a close, slightly high viewpoint. For a more documentary feel, ask for a low camera at lawn level, so the capybaras look larger against the skyline.
Lens
28mm gives a wide view with mild perspective stretch, so the front animals look big and the tower stays small behind them. Change to 50mm for less distortion and a tighter crop.
Light
Warm evening sunlight gives soft side light and gentle shadows on the fur. Say 'golden hour backlight' for a glowing rim, or 'overcast afternoon' for flatter, calmer tones.
Mood
'Deadpan holiday charm' keeps the faces calm rather than cartoonish. Replace it with 'joyful' if you want wider eyes and a more excited tourist photo.

Variations on the scene

Blue hour

Moves the scene to dusk with the tower lights on; good for a moodier, night-trip look.

Prompt

Wide 16:9 landscape frame. Three capybaras cluster shoulder to shoulder on a Paris lawn as though posing for a cheerful selfie, one curious, one sleepy and one looking slightly away, with the Eiffel Tower softly lit behind them. Keep their full heads and front paws naturally proportioned. Blue hour dusk, warm tower lights, playful 28mm wildlife photography, deadpan holiday charm, no text.

Spring low angle

Changes season and camera position for a fresher, more heroic view.

Prompt

Wide 16:9 landscape frame. Three capybaras cluster shoulder to shoulder on a Paris lawn dotted with white blossoms, shot from a low camera at grass level, one curious, one sleepy and one looking slightly away, with the Eiffel Tower softly visible behind them. Keep full heads and front paws naturally proportioned. Soft morning light, 28mm wildlife photography, no text.

Different subject

Swaps the central animal while keeping the structure; use it to test how the same staging works with a smaller, fluffier subject.

Prompt

Wide 16:9 landscape frame. Three red pandas cluster shoulder to shoulder on a Paris lawn as though posing for a cheerful selfie, one curious, one sleepy and one looking slightly away, with the Eiffel Tower softly visible behind them. Keep their full heads and front paws naturally proportioned. Warm evening sunlight, playful 28mm wildlife photography, cream stone and fresh green surroundings, no text.

Model and settings

Keep 16:9, because the wide frame has room for three animals and the tower together. Keep quality on high, since fur texture and the soft tower background both benefit from detail. For a phone-style selfie, try a vertical ratio, but then ask for the tower to be tall behind the group. If you need a print or banner, raise the resolution when the option is available.

  • Nano Banana 2.1Pick it if you want sharp 4K output of the same scene, especially if you later add a caption or sign, since it is known for crisp text.
  • FLUX.2 ProChoose it when you want a more photoreal wildlife look, with fur and light that read like a real camera shot.

When the scene falls apart

The Eiffel Tower looks too large or too sharp and competes with the animals.
Keep 'softly visible behind them' and add 'shallow depth of field, tower small in the distance' so the capybaras stay the focus.
One capybara has a cropped head or odd paws.
Repeat the anatomy line and add 'all three faces fully in frame, both front paws visible' to make the group easier to read.
All three faces look the same.
Make the moods stronger: 'left one wide-eyed and curious, middle one eyes half closed, right one glancing away to the side'.
Signs or captions appear on the lawn or buildings.
Keep 'no text' at the end and add 'no signs, no lettering, no watermark' to remove any stray writing.

Questions about this scene prompt

Why do the capybaras look like they are taking a selfie?

The words 'shoulder to shoulder' and 'posing for a cheerful selfie' push the model to pack the animals close and face the viewer. No phone is described, so the selfie feeling comes from the grouping alone.

Can I use a different landmark instead of the Eiffel Tower?

Yes. Change 'Paris lawn' and 'Eiffel Tower' together, for example to a London park with Big Ben, so the setting stays consistent. Keep 'softly visible' so the landmark stays in the background.

Why does the prompt say no text?

Image models often add signs, captions or fake lettering to tourist scenes. GPT Image 2.5 Sunburst can render text well, so ending with 'no text' tells it to leave the frame clean.