
Turn a face into a carved jack-o'-lantern to print
Add a photo to start
How this template works
Image Studio carves the face from your photo into a jack-o'-lantern, then Image to 3D builds a solid pumpkin you can print and paint.
1Open Image StudioStep 1 · Image StudioCarve the pumpkin
Image Studio turns the face into a carved relief on the front of a round, ribbed pumpkin with a stem, keeping it recognisable.
GPT Image 2.5 Flare · low quality · 1K
2Open Image to 3DStep 2 · Image to 3DBuild the 3D model
Image to 3D (Prism 3.1) builds the pumpkin with Fast textures and Standard mesh quality.
Prism 3.1 · Fast textures · Standard mesh
Tips for the best result
- A front-facing close-up of the face works best.
- Pets with clear markings make the cutest pumpkins.
- Print a family row of pumpkins for the porch or mantel.
Do it yourself for more control
- Ask for a spooky or a goofy expression in the Image Studio prompt.
- Print in orange PLA, or in white and paint it.
- To light it up, hollow it in your slicer settings or Print Export and add a tea light.
Good to know
The pumpkin is solid; the carving is a relief on the surface, not cut through.
Made with this template
The photo in the corner of each one is what went in.




Each example is an actual run of this template at Standard quality, made from a realistic sample photo.
Run this template from Claude, ChatGPT or Cursor
Connect the 3D AI Studio MCP to your AI assistant and paste the brief into the chat. It runs the same steps with the same prompts and settings, shows you the result in the conversation and saves it to your library.
- Connect the MCP once in your account settings. It's included in every paid plan.
- Copy the brief.
- Paste it into a new chat. Your assistant opens an upload card for your photo, then runs every step.
upload_imageedit_image_gptgenerate_prism_3_1convert_modelget_generationshow_generationUse the 3D AI Studio MCP to run the "Pumpkin Portrait" template (https://www.3daistudio.com/templates/3d-printed-pumpkin) for me. My photo(s): I'll hand them over when you call upload_image. Subject: Person Expression: Friendly Pumpkin shape: Round Follow these steps in order. The prompts and settings are the template's own, so use them word for word. 1. Get my photos Call upload_image with purpose "Photo for the Pumpkin Portrait template" so I can hand them over (images attached in the chat don't reach the MCP). I can upload up to 3 photos of the same subject; use all of them. 2. Carve the pumpkin Call edit_image_gpt with my uploaded photo(s) in images, quality "low", output_format "png" and this prompt: """ The reference photo(s) show one person; that person is the subject. Keep them clearly recognisable: same face, facial features, hairstyle, hair colour, skin tone, glasses or beard and body proportions. Only the outfit and styling change as described. Create a single carved jack-o'-lantern pumpkin sculpture whose carved face is a recognisable portrait of the subject: the front of the pumpkin is carved as a stylized relief of the subject's face and hair (or the animal's face, ears and markings), friendly and smiling, with a short curly stem on top. A round, ribbed, solid pumpkin sitting flat on its base, frontal three-quarter view, the entire pumpkin visible with generous empty margin. Isolated on a seamless pure white (#FFFFFF) background, soft even studio lighting, no shadows on the background, no text. Light and surfaces: soft, even, diffuse studio light from the front, and at most a soft satin sheen: no mirror-like gloss, no bright white hot spots or glare, and no reflections of lights, windows or surroundings. """ 3. Build the 3D model Call generate_prism_3_1 with the task_id of the image from step 2 in images, texture_model "3.5", texture_quality "fast", geometry_quality "standard", pbr false, lighting_removal false. 4. Export Export it for printing: call convert_model on the 3D model with output_format "3mf" (or "stl" if I ask for it), plus max_size and unit "cm" if I gave you a print size. After each generation call, keep polling get_generation with its task_id until it completes, then show me the result with show_generation before you start the next step.
Or automate it with the API
The same tools are available through the 3D AI Studio API. Call them from your own code to make hundreds at once, build them into your app or run them in your pipeline.
Similar templates
More templates like Pumpkin Portrait, ready to use the same way.







