Nano banana 2 on Gemini app...
Reference image from @saniaspeaks_View Original

Copy this Nano Banana Pro text-to-image prompt to create portrait...

Text-to-Image

Prompt

Nano banana 2 on Gemini app. Prompt: Photorealistic smartphone selfie of a beautiful young East Asian woman with fair porcelain skin, a messy low bun, wispy bangs, and a small white flower hair clip. She wears pearl drop earrings and a gray knitted sleeveless high-neck sweater with a small flower detail at the collar. Soft Korean makeup, rosy cheeks, and glossy lips. Cozy modern bedroom background with warm ambient lighting and a glowing lamp behind her. Slightly low-angle selfie perspective, soft background blur, natural iPhone camera aesthetic, candid handheld snapshot, realistic skin texture, ultra-realistic, vertical 3:4.

How This Prompt Works

Copy this Nano Banana Pro text-to-image prompt to create portrait concepts in indoor scenes with photorealistic detail. Best in 9:16 framing. Ready for...

Keep the base prompt intact for the first run, then iterate on one variable at a time so the composition stays stable. Keep the generator on 9:16 for the closest match. The mood is anchored by cozy modern bedroom background with warm ambient lighting and a glowing lamp behind her.

Best Settings

Recommended Aspect Ratio
9:16
Recommended Style
Photorealistic
Negative Prompt
ugly, deformed, low quality, blurry, text, watermark, worst quality, low res
Recommended Model
Nano Banana Pro

What to Change First

  • Change the subject block first: Photorealistic smartphone selfie of a beautiful young East Asian woman with fair porcelain skin, a messy low bun, wispy...
  • Adjust the mood through light and backdrop cues: Cozy modern bedroom background with warm ambient lighting and a glowing lamp behind her.
  • Keep the finish constraints aligned while you test variants: She wears pearl drop earrings and a gray knitted sleeveless high-neck sweater with a small flower detail at the collar.

Before You Generate

Note 1

Use 9:16 on the first run, then test alternate crops after the base composition is working.

Note 2

Lock the environment before fine styling changes: Cozy modern bedroom background with warm ambient lighting and a glowing lamp behind her.

Best For

  • Portrait studies, beauty concepts, and tightly framed editorial references.
  • Text-to-image ideation when you want a reliable starting frame in 9:16.
  • Realism-heavy outputs where believable materials, skin, or product finishes need to hold up in close view.

Skip This Prompt If

  • You need a wide environment shot or multiple subjects competing for attention in the same frame.
  • You need to begin with a radically different crop than 9:16 instead of honoring the existing composition hints.
  • You want a loose multi-subject scene instead of a prompt built around one controlled focal point.

Mistakes to Avoid

  • Ignoring the recommended 9:16 crop on the first run. The prompt's composition cues were written for that frame.
  • Changing subject, lighting, and finish together. You lose the stable base that makes the prompt reusable.
  • Dropping the lighting or backdrop cues too early. Those clauses usually carry most of the mood and depth.

3 Ways to Adapt This Prompt

Use these as safe starting edits so you keep the prompt's structure while still making it your own.

Swap the subject, keep the frame

Replace photorealistic smartphone selfie of a beautiful young east asian woman with fair... with your own subject while leaving the camera and composition cues intact.

Retune the mood, not the structure

Keep the subject block, then rewrite cozy modern bedroom background with warm ambient lighting and a glowing lamp behind her. to move the image into a new lighting setup.

Change the finish without breaking geometry

Test a new texture or rendering finish by rewriting she wears pearl drop earrings and a gray knitted sleeveless high-neck sweater with a... while leaving the scene structure alone.

Generate This Image

Use our professional tools to tweak this prompt and generate your own version in seconds.

GPT Image 2 Generator

GPT Image 2 Generator
Reference Image(0/9)
634 / 8000
Cost 4 creditsRemaining 0 credits
Image Preview

No Images Generated