
Turn your child's photo into a clean daycare or preschool ID portrait. Crisp white shirt with a beige backdrop in standard ID-portrait framing. Pick from multiple background colors and hair styles for various use cases.
Prompt
[Input]
- output_size: 1024x1024 (1:1 square, ID portrait framing)
- reference: 1 Korean child's photo (front-facing, clear face recommended)
[Purpose]
Convert the user's attached child photo into a clean studio-style ID portrait suitable for daycare, preschool, academy registration, or passport drafts. The child appears from chest up against a soft solid backdrop with a subtle vignette in classic Korean kindergarten ID photo composition.
[Scene — image-to-image edit, preserve identity]
Use the user's attached photo as the base. PRESERVE the child's identity (face proportions, eye shape, age, hair style, skin tone) and redraw as a clean photorealistic ID portrait. The child must remain recognizably the same.
Child wears a crisp white oxford dress shirt with a clean pointed collar, neatly pressed, no patterns, no logos. Hair: {hair_description}.
Pose: chest-up framing with the head fully visible, approximately 10% empty headroom above the hair, shoulders visible at the bottom edge. Straight-on frontal angle, eye-level camera. Soft neutral expression with a very gentle smile, eyes looking directly at the camera.
Setting: solid {background_color_description} studio backdrop with a subtle soft vignette (slightly darker toward the corners, classic studio look). No props, no objects, no patterns in the background.
Lighting: soft flattering studio lighting, frontal key light with mild fill, gentle catchlights in the eyes. No harsh shadows on the face or backdrop.
[Style]
- Photorealistic clean studio ID portrait
- Color palette: backdrop color plus neutral white shirt, natural skin tones
- No film grain, no creative effects — clean ID photo finish
[Composition]
- 1:1 square (1024x1024)
- Chest-up framing, head fully visible with approximately 10% empty headroom above the hair
- Shoulders visible at the bottom edge
- Subject perfectly centered
- Solid backdrop with subtle corner vignette only
[Text]
- No text anywhere
- No watermarks, no logos, no stamps
- Clean ID portrait only
[🚫 PROHIBITED]
- Branded characters or IP
- Heavy facial restructuring or beautification
- Modern anime, manga, 3D, or chibi style
- Props or accessories beyond the white dress shirt
- Patterns, gradients, objects, or text in the background
- Real brand logos on the outfit
Click to open ChatGPT with the prompt auto-filled.
Click the "Open in ChatGPT" button on the prompt box. A new chat opens with the prompt pre-filled. Drag your photo and send to generate the result.
Face preservation is a known weakness of ChatGPT. Retry with the same prompt or use a clearer front-facing photo. Gemini 2.5 Flash Image (Nano Banana) tends to be more stable.
ChatGPT Korean text rendering is still imperfect. Emphasize "make Korean text clearly readable" or switch to English for stability.
In ChatGPT, ask for "another variation" or "another variation" to retry with the same prompt.
Output resolution is sufficient for A4, 5×7, and 8×10 inch prints. For KakaoTalk sharing, add "1:1 square ratio" to the prompt.