Promptpan

All · Comics & illustration · Characters

548My photo as a boxed block figure

Keep your portrait as an original angular block collectible with a name and two accessories.

Fill in the fields

  1. 1Fill in the fields
  2. 2Copy the prompt
  3. 3Paste it into a GPT chat
  4. 4Send it as is and you get an image like the thumbnail example
  5. 5Attach One photo of yourself with the prompt and your photo is used in the result Optional
Ideas
Ideas
Output format

Choose a mode, then set the size.

Tested by us

Test date
2026-10-28
Tool
ChatGPT image model (run in Codex). Model equivalence and limit differences versus free ChatGPT were not checked in this test.
Result
Pass
What worked
In the final result, 「모아」 appears accurately once inside the nameplate. The figure on the left and the camera and folded umbrella in separate recesses on the right are fully visible. The full body includes both feet and two closed fists without holes, with angular three-dimensional blocks. Teal glasses, a black bob with lighter strands, skin tone, mustard jacket and burgundy top follow the source. No extra text, prices, dates or logos. There is visible space around the nameplate, with the window and objects below it. 1122:1402 is 4:5 within pixel rounding.
What did not work
None under the final revised wording. The first 2 images failed numerical nameplate/window placement; the next 2 failed the text-free top 12%. All 4 remain archived. This is a block simplification of recognizable features, not an identical face replica. The final promise uses relative placement and visible margins; it does not claim to pass the former percentage requirements.
How to improve
If the nameplate drifts, use the final wording defining the nameplate/window relationship and space around the lettering rather than detailed percentages. In the test the name appeared once without clipping. 「모아」 and the camera plus folded umbrella were correct in all 5 attempts.
Actual test result 1
Actual test result 1

After generating · Check the name, identity and two accessories before saving.

Full prompt 4,257 characters
Generate exactly ONE finished image now, using image generation directly. Do not explain, ask questions, output code or require assembly.
Use the selected aspect ratio: Output size 1080x1350 pixels, 4:5 portrait, Instagram standard.. Default is 4:5. Fill the frame edge to edge with one original boxed block toy figurine, one full body and exactly two accessories. No comparison, photo inset, second figure or extra page in the user result.
PHOTO RULE: if a photo is attached, transform that consenting person's visible face proportions, skin tone, apparent age, hair silhouette, eyewear, facial hair and outfit colors into the block figure. Preserve identity rather than replacing the person with a generic avatar. If no photo is attached, invent an entirely fictional adult unrelated to any celebrity; never stop or ask for a photo. The photo field is attachment guidance, not visible copy: "【Photo】". For an unclear group photo use only a clearly indicated subject; otherwise invent a fictional adult without claiming it is the user. Do not infer sensitive personal facts.
Fixed medium: premium original illustrated 3D matte block toy, beveled octagonal head, faceted hair, rectangular torso, articulated square arms and wedge feet. Simplify facial details while preserving identity. Avoid cylindrical stud heads, clamp-shaped hands, branded connector systems and recognizable existing toy silhouettes. Use two solid closed faceted fists, without any open C-shaped gap, hook, clamp or gripping hole. One head, two arms, two legs. No artist or franchise imitation.
Packaging: invent one angular folded-paper window box with a broad clear window, figure on the left and exactly two separate fitted accessory recesses on the right. Figure and accessories fill their compartments; keep the entire figure visible. No real packaging trade dress, product logos, branded clothes or existing character costumes. Invent accessory geometry too. No barcode, certification, age rating, prices, dates, series numbers, claims or decorative lettering.
Box name is "【Box name】". Render it exactly once in English, large and readable inside a separate horizontal name panel above the display window, with blank padding around every letter and generous blank packaging above the panel. Keep the entire name away from all image edges. Place the display window below the name panel and keep the entire figure and both accessories visible inside it. If empty, omit all lettering and the label panel. If it equals "Choose for me", choose one short original personal nickname in English and render only the resolved name, never the control. Do not invent extra words. Keep all essential text fully inside the name panel with visible blank padding, never clipped by the image boundary.
The two accessory inputs are "【Two accessories】". Render these as physical miniature objects, never printed labels. If blank or "Choose for me", choose two different simple unbranded objects. If only one object is supplied, keep it and choose a second complementary one. If more than two are supplied, use only the first two. Never duplicate an accessory or add more. For a brand request replace the brand with an original generic object of a different shape.
Choose box palette, surrounding light and understated setting from the actual outfit colors and accessory subject: plant tools suggest fresh daylight, camera and umbrella suggest a cool rainy evening, thermos and map suggest warm outdoor morning light. Without clear cues use a bright studio. This changes atmosphere only: the illustrated matte block medium, one-box format and accessory count stay fixed. Background is secondary, packaging nearly fills the image, no empty page margin or phone mockup.
Before finishing, check name spelling one character at a time, exactly two accessories, full body, identity continuity, clean unbranded surfaces and no extra writing. Deliver the image itself in this single response.

[Final output format]
Output size 1080x1350 pixels, 4:5 portrait, Instagram standard.
This selected output format takes priority over any fixed canvas size or aspect ratio elsewhere in this template. Adapt the composition, text zones and margins to the selected canvas without stretching or cropping essential content. Device safe areas apply only when a device is selected. Never print these format instructions on the image.

Browse more cards

How to use it · FAQ

Use it

Turn a permitted portrait into one original boxed block collectible image for a profile post or a personal keepsake. This produces artwork, not a physical toy or a manufacturing plan. Hair, glasses, facial hair, age and clothing colors remain recognizable in angular matte forms.

Fill the fields

No field is mandatory. Photo is an attachment reminder; typing in it does not upload a file. Use a clear face-and-upper-body photo of one consenting adult. Box name appears once. Clear it for no lettering, or use Choose for me for a short fictional nickname. Separate two accessories with a comma. An empty accessory field selects two objects; one supplied object gains a complementary second; more than two uses the first two only.

Send once

Attach the photo and paste the copied prompt into the same image-AI message, then send once. Without an attachment, the prompt creates a fictional adult. The default ratio is 4:5; change it with the shared ratio menu. Outfit colors and accessories guide the atmosphere while the illustrated matte block style stays fixed. Avoid clothing logos and personal name tags in the source photo.

Read the examples

The first gallery image is a separate pure result: a fictional adult with braids and a lavender jumpsuit, a sketchbook and a brush. The second compares a fictional portrait with its rainy evening figure, retaining teal glasses, a short bob and a mustard jacket; accessories are a camera and a folded umbrella. The third retains another fictional adult's gray curls, beard and coral scarf in warm outdoor light, with a thermos and a folded map. All Korean sample packages say the example name; an English output uses Haru. Comparison images explain identity preservation; your output is one complete box, without the source portrait.

Check and refine

Read the name letter by letter and count exactly two accessories. Compare age, hair, glasses and outfit to the photo. Check that both feet and the entire box are visible, with no extra person or stray text. If the face looks too young, request the original apparent age and facial hair. If extra items appear, request only the first two accessories. Corrections are optional refinements after the first finished image.

Questions

This is an invented design rather than a replica of a commercial toy. Do not request celebrities, existing characters, brands or an artist's style. Use only photos you are allowed to transform and publish. Check the external image service's terms and pricing there. For a group photo, clearly identify the intended subject before sending.