CheshireJCat/create-3d-model-skill / skills/create-3d-model/references/modules/reference-to-3d
reference-to-3d
VerifiedReconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic front/side/back/top views, or mascot/logo art where visual fidelity to the source is more important than a plausible generated object. Use when the user says the model must match a template, wireframe, texture pack, character sheet, mascot sheet, or brand asset exactly; also use after feedback like "does not look like the reference", "fit the texture 1:1", "wrong number of visible parts", or "compare against the template". Requires Blender MCP plus local Python with Pillow/OpenCV/numpy; pairs with blender-uv-texturing, wireframe-to-3d, blender-modeling, blender-materials, and blender-export.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.3 KB |
| references/overview.md | markdown | 1.3 KB |
| scripts/silhouette_validator.pyexecutable | script | 2.3 KB |
| scripts/template_analyzer.pyexecutable | script | 4.5 KB |
scripts/silhouette_validator.py
View on GitHub#!/usr/bin/env python3
"""Compare reference and render masks for template-locked validation."""
import argparse, json
from pathlib import Path
import cv2
import numpy as np
try:
from skimage.metrics import structural_similarity as ssim
except Exception:
ssim = None
def mask(path, threshold=20):
img = cv2.imread(str(path), cv2.IMREAD_UNCHANGED)
if img is None:
raise FileNotFoundError(path)
if img.ndim == 3 and img.shape[2] == 4:
m = img[:, :, 3]
else:
rgb = img[:, :, :3] if img.ndim == 3 else cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
gray = cv2.cvtColor(rgb, cv2.COLOR_BGR2GRAY)
_, m = cv2.threshold(gray, threshold, 255, cv2.THRESH_BINARY)
return (m > 0).astype(np.uint8)
def bbox(m):
ys, xs = np.where(m > 0)
if len(xs) == 0:
return [0,0,0,0], [0.0,0.0]
x0,x1,y0,y1 = xs.min(), xs.max(), ys.min(), ys.max()
return [int(x0), int(y0), int(x1-x0+1), int(y1-y0+1)], [float(xs.mean()), float(ys.mean())]
def main():
ap = argparse.ArgumentParser()
ap.add_argument('--reference', required=True)
ap.add_argument('--render', required=True)
ap.add_argument('--out', required=True)
ap.add_argument('--threshold', type=int, default=20)
args = ap.parse_args()
a = mask(args.reference, args.threshold)
b = mask(args.render, args.threshold)
if a.shape != b.shape:
b = cv2.resize(b, (a.shape[1], a.shape[0]), interpolation=cv2.INTER_NEAREST)
inter = np.logical_and(a, b).sum()
union = np.logical_or(a, b).sum()
iou = float(inter / union) if union else 0.0
ba, ca = bbox(a); bb, cb = bbox(b)
center_dist = float(np.linalg.norm(np.array(ca) - np.array(cb)))
mse = float(np.mean((a.astype(np.float32) - b.astype(np.float32)) ** 2))
ssim_val = float(ssim(a, b, data_range=1)) if ssim is not None else None
out = {
'reference': args.reference,
'render': args.render,
'iou': iou,
'mse': mse,
'ssim': ssim_val,
'reference_bbox': ba,
'render_bbox': bb,
'reference_centroid': ca,
'render_centroid': cb,
'centroid_distance_px': center_dist,
}
Path(args.out).write_text(json.dumps(out, indent=2))
print(json.dumps(out, indent=2))
if __name__ == '__main__':
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |