Gpt Image 2 Nano banana 2...
Reference image from @AiWithTariqView Original

Copy this Nano Banana Pro reference-guided prompt to create portrait...

Image-to-Image

Prompt

Gpt Image 2 | Nano banana 2 | Grok | Gemini Prompt Use the uploaded image as the exact identity reference. Preserve the person's identity with extremely high accuracy. Keep the face 100% recognizable. Do not change the hairstyle, beard, facial structure, eyes, eyebrows, nose, lips, jawline, skin tone, age, or facial proportions. Create a premium ultra-realistic graphite pencil sketch in 9:16 vertical format. A successful young South Asian AI entrepreneur standing proudly beside a brand-new matte black Lamborghini outside an ultra-luxury supercar dealership during golden hour. A dealership representative is handing him the luxury car key while he accepts it with a confident smile. The showroom behind him features exotic supercars, floor-to-ceiling glass walls, and elegant architecture. Warm sunlight reflects beautifully across the car, creating a cinematic luxury atmosphere. He wears a tailored charcoal double-breasted suit over a fitted black turtleneck, polished leather Chelsea boots, a luxury stainless-steel wristwatch, and a minimalist bracelet. Museum-quality graphite pencil rendering with ultra-fine cross-hatching, realistic reflections, cream textured sketchbook paper, visible construction lines, unfinished artistic sketch edges, editorial luxury portrait, masterpiece, hyper realistic, ultra detailed, 16K. Negative Prompt: low quality, blurry, cartoon, anime, CGI, watercolor, oil painting, distorted face, extra limbs, watermark, logo, text.

How This Prompt Works

Copy this Nano Banana Pro reference-guided prompt to create portrait concepts with editorial styling and photorealistic detail. Best in 9:16 framing. Built...

Use a clean reference image with obvious subject edges and readable facial or product details before you start changing the styling. Keep the generator on 9:16 for the closest match. The mood is anchored by low quality, blurry, cartoon, anime, cgi, watercolor, oil painting, distorted face, extra limbs, watermark,...

Best Settings

Recommended Aspect Ratio
9:16
Recommended Style
Editorial, Photorealistic, Cinematic, Minimalist
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: low quality, blurry, cartoon, anime, CGI, watercolor, oil painting, distorted face, extra limbs, watermark, logo, text.
  • Adjust the mood through light and backdrop cues: low quality, blurry, cartoon, anime, CGI, watercolor, oil painting, distorted face, extra limbs, watermark, logo, text.
  • Keep the finish constraints aligned while you test variants: low quality, blurry, cartoon, anime, CGI, watercolor, oil painting, distorted face, extra limbs, watermark, logo, text.

Before You Generate

Note 1

Start with a sharp reference image. This prompt is written to preserve source identity, silhouette, or product structure before stylization.

Note 2

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

Note 3

This prompt suppresses text or logos. Remove that constraint before asking for branded packaging, typography, or visible watermarks.

Best For

  • Portrait studies, beauty concepts, and tightly framed editorial references.
  • Reference-image workflows where identity, product shape, or silhouette should survive the restyle.
  • 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.
  • Your reference image is low-resolution, badly lit, or cluttered enough to break subject preservation.

Mistakes to Avoid

  • Ignoring the recommended 9:16 crop on the first run. The prompt's composition cues were written for that frame.
  • Using a muddy reference image and expecting the prompt to repair identity, silhouette, or packaging structure on its own.
  • Asking for readable type, logos, or packaging text without first removing the no-text constraint.

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 low quality, blurry, cartoon, anime, cgi, watercolor, oil painting, distorted face,... with your own subject while leaving the camera and composition cues intact.

Retune the mood, not the structure

Keep the subject block, then rewrite low quality, blurry, cartoon, anime, cgi, watercolor, oil painting, distorted face,... to move the image into a new lighting setup.

Push the restyle with a cleaner reference

Start from a sharper or more contrasty source image, then edit finish descriptors only after subject preservation is stable.

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)
1478 / 8000
Cost 4 creditsRemaining 0 credits
Image Preview

No Images Generated