Nano Banana Pro on httpwondash prompt...
Reference image from @DiamondZPetSpaView Original

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

Text-to-Image

Prompt

Nano Banana Pro on http://wonda.sh prompt: { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle Korean beauty aesthetic, natural candid photography, soft golden sunset ambiance, lifestyle influencer vibe", "scene": { "location": "busy Seoul downtown street near Starbucks during sunset golden hour", "environment": "warm orange-pink sunset sky, glowing city lights beginning to appear, modern Korean street atmosphere, blurred pedestrians, Starbucks storefront in background, cinematic urban evening mood" }, "subject": { "ethnicity": "Korean", "appearance": { "hair": "messy blonde loose tied hair with soft strands falling around face", "skin": "fair glowing skin with natural texture and subtle freckles", "eyes": "light blue eyes", "expression": "soft relaxed subtle pout, natural candid expression", "makeup": "minimal clean girl makeup, glossy lips, soft blush" }, "pose": "holding smartphone with one hand taking selfie, slightly angled camera perspective", "outfit": { "top": "cream ribbed fitted crop top", "outerwear": "light pastel blue oversized cardigan", "bottom": "high waist white shorts", "accessories": "minimal gold necklace" } }, "props": { "drink": "large Starbucks iced coffee cup with visible logo and green straw" }, "camera": { "device": "iPhone 16 Pro front camera", "angle": "close-up handheld selfie shot", "framing": "9:16 vertical composition, upper body visible", "focus": "sharp focus on face with softly blurred city background", "effects": "slight amateur motion softness, natural lighting, realistic skin details, cinematic bokeh" }, "quality": { "resolution": "8k", "render": "photorealistic", "details": "highly detailed skin texture, realistic lighting, natural shadows, subtle depth of field" } } }

How This Prompt Works

Copy this Nano Banana Pro text-to-image prompt to create portrait concepts in urban street scenes with photorealistic detail and cinematic lighting....

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 { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle korean beauty aesthetic, natural...

Best Settings

Recommended Aspect Ratio
9:16
Recommended Style
Photorealistic, Cinematic, Minimalist, 3D Rendered
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: { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle Korean beauty aesthetic, natural candid...
  • Adjust the mood through light and backdrop cues: { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle Korean beauty aesthetic, natural candid...
  • Keep the finish constraints aligned while you test variants: { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle Korean beauty aesthetic, natural candid...

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: { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle Korean beauty aesthetic, natural...

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.
  • Cinematic, mood-first outputs where light direction carries a lot of the final image quality.

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 { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle korean... with your own subject while leaving the camera and composition cues intact.

Retune the mood, not the structure

Keep the subject block, then rewrite { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle korean... to move the image into a new lighting setup.

Change the finish without breaking geometry

Test a new texture or rendering finish by rewriting { "prompt": { "style": "ultra realistic amateur smartphone selfie, subtle korean... 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 生成器

GPT Image 2 生成器
参考图片(0/9)
1981 / 8000
消耗 4 积分剩余 0 积分
图片预览

没有生成图片