D&D Miniature Maker

Use the 3D AI Studio MCP to run the "D&D Character Miniature" template (https://www.3daistudio.com/templates/dnd-character-miniature) for me.

My idea: A half-elf bard with a feathered hat and a red cloak
Race: Human
Class: Fighter
Pose: Ready
Mount: On foot
Base: Plain
Finish: Painted

Follow these steps in order. The prompts and settings are the template's own, so use them word for word and only put my idea where it says {MY IDEA}.

1. Design my character
Call generate_image_nano_2_1 with aspect_ratio "1:1", resolution "1K", output_format "png" and this prompt:
"""
Character: {MY IDEA}. A single tabletop roleplaying miniature of one player character: heroic 28-32 mm scale proportions (slightly enlarged head, hands and weapon), the race readable at a glance from the silhouette (ears, horns, height, build, tail) and the class from its signature gear, which stays chunky and close to the body. Standing on a round flat 25 mm base unless a mount is described. Crisp sculpted detail suitable for resin printing, no thin fragile parts sticking out. The entire miniature and base visible, centered, three-quarter front view, generous empty margin. Isolated on a seamless pure white (#FFFFFF) background, soft even studio lighting, no shadows on the background, no text. Race: human, average height and build. 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. Class: fighter in practical plate-and-leather armour with a longsword and a round shield. Finish: painted in rich natural colours like a finished display miniature, with washes and edge highlights.
"""
If I want to start from a sketch or reference image instead, call upload_image so I can hand it over, then call edit_image_gpt with the upload in images, quality "low", output_format "png" and this prompt:
"""
The reference image shows the character to make: character art, a sketch, or a photo of the player. Keep its look recognisable: face, hairstyle, hair and skin colour, outfit colours and signature gear; a real person keeps their facial likeness but is re-created in the miniature's sculpted, painted style, never with a photographic face. A single tabletop roleplaying miniature of one player character: heroic 28-32 mm scale proportions (slightly enlarged head, hands and weapon), the race readable at a glance from the silhouette (ears, horns, height, build, tail) and the class from its signature gear, which stays chunky and close to the body. Standing on a round flat 25 mm base unless a mount is described. Crisp sculpted detail suitable for resin printing, no thin fragile parts sticking out. The entire miniature and base visible, centered, three-quarter front view, generous empty margin. Isolated on a seamless pure white (#FFFFFF) background, soft even studio lighting, no shadows on the background, no text. Race: human, average height and build. 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. Class: fighter in practical plate-and-leather armour with a longsword and a round shield. Finish: painted in rich natural colours like a finished display miniature, with washes and edge highlights.
"""

2. Build the 3D model
Call generate_prism_3_1 with the task_id of the image from step 1 in images, texture_model "3.5", texture_quality "fast", geometry_quality "standard", pbr false, lighting_removal false.

3. 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.