Made with GPT Image 2 in ChatGPT by Library Avatars. Promptclay never generates images.
Did it work?
No reports yet. Tell others if it worked for you.
Character Consistency 9-Grid Collage
Prompt
3 blanks to fillPlease make the person/character in the attached reference image the protagonist. Whether the reference image is live-action or an illustration, naturally convert it to match the specified "{output_style}". Maintain the main features of the reference image such as facial features, hairstyle, hair color, eyes, contour, sense of age, atmosphere, body shape, and costume, so that they appear to be the same person/character in every frame. The output should be a single image with an "{aspect_ratio}". Divide the entire screen into equal 3 columns x 3 rows, and ensure it is a collage of exactly 9 frames in total. Do not increase or decrease the number of frames; keep the layout organized and easy to view. Each frame should look like a different moment captured of the same person/character. Vary the angle, distance, expression, and movement with shots like close-up, bust-up, slightly pulled back composition, profile, looking back, walking, eyes looking away, natural smile, and relaxed poses. The background should be based on "{background}", with a clean and bright atmosphere. The overall impression should be "refreshing," in a light and breezy visual diary style. Overlay thin, white, hand-drawn style lines throughout. The white lines should flow and connect across the 9 frames, surrounding the person or expressing movement. Include small hearts, star-shaped sparkles, wavy lines, and motion lines. However, do not hide the face, eyes, or expressions. Elements to avoid: text, subtitles, logos, watermarks, extra people, turning into a different person, facial distortion, limb failure, cluttered backgrounds, excessively dark shadows, scribbles hiding the face, and frames other than the 9 segments.
Preview of your prompt
Please make the person/character in the attached reference image the protagonist. Whether the reference image is live-action or an illustration, naturally convert it to match the specified "photorealistic style". Maintain the main features of the reference image such as facial features, hairstyle, hair color, eyes, contour, sense of age, atmosphere, body shape, and costume, so that they appear to be the same person/character in every frame. The output should be a single image with an "1:1". Divide the entire screen into equal 3 columns x 3 rows, and ensure it is a collage of exactly 9 frames in total. Do not increase or decrease the number of frames; keep the layout organized and easy to view. Each frame should look like a different moment captured of the same person/character. Vary the angle, distance, expression, and movement with shots like close-up, bust-up, slightly pulled back composition, profile, looking back, walking, eyes looking away, natural smile, and relaxed poses. The background should be based on "bright interior", with a clean and bright atmosphere. The overall impression should be "refreshing," in a light and breezy visual diary style. Overlay thin, white, hand-drawn style lines throughout. The white lines should flow and connect across the 9 frames, surrounding the person or expressing movement. Include small hearts, star-shaped sparkles, wavy lines, and motion lines. However, do not hide the face, eyes, or expressions. Elements to avoid: text, subtitles, logos, watermarks, extra people, turning into a different person, facial distortion, limb failure, cluttered backgrounds, excessively dark shadows, scribbles hiding the face, and frames other than the 9 segments.
DetailsVersions, settings and questions
Written for
What's in the prompt
- Subject
- Model
- GPT Image 2
If your face changes
keep my face exactly the sameQuestions
- Does this work in the ChatGPT app?
- Yes. Paste the prompt and attach your photo if it uses one.
- It changed my face. What do I do?
- Add "keep my face exactly the same" to the end and run it again.
- Can I use the images I make?
- Check the terms of the app you use. Promptclay never generates images and claims nothing you make.
























