Use the 3D AI Studio MCP to run the "Pet Memorial" template (https://www.3daistudio.com/templates/pet-memorial-figurine) for me.

My photo(s): I'll hand them over when you call upload_image.
Style: Sleeping
Base: 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 Pet Memorial template" so I can hand them over (images attached in the chat don't reach the MCP). I can upload up to 5 photos of the same subject; use all of them.

2. Design the memorial
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 animal; that animal is the subject. Keep this individual animal completely intact: same coat pattern and fur colours, eye colour, face, ears, tail, proportions, species and breed. Its coat pattern is what makes it this animal and not just any of its breed: every patch, stripe, spot, mask, blaze and white sock stays exactly where it is in the photo(s), with the same size, shape and colour, including marks on only one side (for example a white patch around one eye only, or one dark ear). Keep the real fur colours and how much of the coat each one covers. Never mirror, move, merge, add or remove a marking, and never replace the pattern with one that is typical for the breed. If several photos show different sides of the animal, take each side's markings from the photo that shows that side. The face, skin, hair, eyes and fur are sculpted, painted and lit exactly like the rest of the figure, in the same style, material, level of detail and colours, so it reads as one object made at once. Never paste the photographic face onto the figure: no photo skin texture, no photo lighting, and no seam, edge or colour shift at the neck. If several photos are provided they all show the same subject from different angles or moments: merge them into ONE consistent figure and pick the clearest features. The photos may be cropped or show only the face or upper body: reconstruct the COMPLETE body anyway, from the top of the head to the feet or paws, including legs, feet, shoes, tail and all limbs, complete and believable at the proportions of the requested style, matching everything visible. Never crop, cut off or hide any part of the body, never show a bust or half figure, and do not leave anything outside the frame. Transform the animal into a gentle memorial figurine that celebrates it: peaceful and loving, never sad, keeping its exact coat pattern, fur colours, face and ears. Chunky, sturdy, softly sculpted shapes with no thin fragile parts, on a round flat base. The entire figurine and base visible with generous empty margin, centered, three-quarter front view. Isolated on a seamless pure white (#FFFFFF) background, soft even studio lighting, no shadows on the background, no text, no writing on the base. Pose: curled up peacefully asleep on a soft round cushion, eyes closed, content. Before finishing, compare the coat with the photo(s): every marking of the real animal is there, in the same place and shape and in the same colours, and none is added, mirrored or moved. 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.