cartoon prompt — Doraemon Photo With Kid Prompts

Copy this cartoon prompt below and paste it into ChatGPT with your own photo.

Prompt
Use Image (uploaded kids photo) as the exact identity reference. Create an ultra-detailed cinematic anime-realism scene inspired by a cozy rooftop terrace setting.
Nighttime rooftop/terrace setting under a deep blue starry sky, glowing moonlight, calm city lights spread across the horizon, soft clouds, cool blue ambience, dreamy silent atmosphere, magical and wonder-filled mood perfectly suited for a child.
Nobita and Doraemon are sitting quietly on the terrace roof, relaxed, peaceful, emotionally calm, looking into the night sky in comfortable silence — like best friends sharing a quiet magical moment together.
Add the child sitting next to Nobita and Doraemon, naturally integrated into the scene as their little companion and best friend. The child is also sitting silently, gazing upward at the stars with wide curious innocent eyes, feeling the peaceful night atmosphere with a soft calm wonder-filled expression. The child's body posture should feel relaxed, cozy, and emotionally present — slightly leaning toward Doraemon or Nobita in a comfortable friendly way, as if they belong together naturally in this world.
The child's head position should be slightly tilted upward, looking toward the sky with a dreamy curious gaze — as if discovering the stars for the first time.
STRICTLY preserve the child's real identity from the uploaded photo — absolutely no face modification whatsoever. Keep the child's exact facial features, face shape, cheeks, nose, lips, eyes, eyebrows, skin texture, hairstyle, hair density, hairline, body proportions, shoulder width, height ratio, innocent personality, and natural physics exactly the same. The child's appearance must remain 100% realistic and human — NOT cartoon or anime styled. The child must look like a real child naturally placed inside an anime world.
Important contrast: Nobita and Doraemon remain authentic anime/cartoon characters. The child remains completely photorealistic and real — a real human child naturally blended into the anime environment through cinematic lighting and warm color grading.
Outfit: Cute comfortable nighttime casual clothing — a soft cozy oversized hoodie or pastel colored sweatshirt, comfortable jogger pants or pajama-style bottoms, small cozy socks visible, warm and adorable nighttime vibe as if the child sneaked out to the rooftop for a secret stargazing adventure with Doraemon and Nobita.
Doraemon should have one arm gently placed near the child in a warm protective friendly gesture, making the child feel safe and included. Nobita should be glancing toward the child with a soft friendly smile, as if welcoming them into their little rooftop gang.
Lighting and Effects: Soft moonlight illumination casting a gentle glow on the child's face, cool blue tones with warm golden undertones from city lights below, subtle rim light outlining the child's silhouette against the night sky, rooftop reflections, gentle glow from city lights, atmospheric depth, starry sky sparkle with a few shooting stars visible, cinematic shadows, calm dreamy magical night mood, soft volumetric lighting, realistic light falloff, warm and safe emotional atmosphere.
Composition: Vertical framing, rooftop tiles visible, cityscape bokeh in background with twinkling city lights, moon and stars above with a large glowing moon as the central light source, Doraemon on one side and Nobita on the other with the child naturally seated between them or beside them, emotional quiet companionship, peaceful magical childhood moment, sense of wonder and adventure.
Style: Ultra-detailed cinematic anime-realism fusion, Makoto Shinkai inspired atmosphere, emotional night aesthetic, high detail, natural light interaction, realistic skin rendering for the child, soft innocent child facial rendering, detailed rooftop textures, depth of field, masterpiece quality, 8K resolution, visually poetic, calm and nostalgic emotional storytelling mixed with childlike wonder and warmth, highly immersive mood, safe wholesome family-friendly image, magical childhood memory aesthetic.

Best with: ChatGPT

This cartoon prompt turns an ordinary photo into a polished cartoon image in a single generation. You get the same look you see above — no editing skills needed. It leans on moody low light, an outdoor setting and a cinematic finish.

What this prompt creates

The instruction places the subject in an outdoor setting, lights them with moody low light, finishes with a cinematic finish and and frames it as a vertical 9:16 frame. At roughly 590 words it is a detailed prompt, so expect the model to follow it closely — either way, the result stays recognisably you because the source photo drives the likeness.

How to use this cartoon prompt

  1. Tap Copy prompt above to copy the full text.
  2. Open ChatGPT and start a new chat.
  3. Upload the photo you want to transform.
  4. Paste the prompt and send it.
  5. If the first result is not quite right, regenerate once or twice — small changes in wording shift the style a lot.

Tips for a better result

  • Match the light. This prompt asks for moody low light, so a source photo shot in similar conditions needs far less correction.
  • Mind the background. It replaces your backdrop with an outdoor setting — a source photo with a plain or blurred background swaps over most cleanly.
  • Shoot for the crop. The output is a vertical 9:16 frame, so leave headroom in your original rather than filling the frame.
  • Try it twice. Image models are random — a second run often looks noticeably better.
  • Start from the highest-resolution copy you have. Detail the model can see is detail it can keep.

Who this cartoon prompt suits

This one works especially well for Girls. It suits Instagram posts, profile pictures, and WhatsApp display photos, and it holds up on both phone and desktop screens.

More prompts like this

Browse every cartoon prompt in this collection, or head back to the PromptPin homepage for the newest AI photo prompts. All of them are free to copy and use.

OpenAI’s guide to image generation

What makes this cartoon style work

Three things do most of the heavy lifting here. The lighting is described precisely rather than left to chance. The framing and camera angle are stated up front, which keeps the subject in proportion. And the finish — grain, contrast, and colour grade — is spelled out at the end, which is what separates a snapshot from something that looks deliberately shot.

You can reuse this structure for your own ideas. Keep the sentence order — subject, setting, lighting, camera, finish — and swap the descriptive words. Prompts written this way behave far more predictably than one long sentence.

See all 225 ai photo prompts for girls →