elithril/blender-kiln / plugin
kiln
FlaggedMakes and fixes 3D assets in Blender, for games, the web and AR. Use when the user wants a 3D model, prop, character or GLB/glTF/FBX/USDZ file made — from a text brief, a reference image, a free marketplace (PolyHaven, Sketchfab) or AI generation — AND when they bring an existing 3D file to fix: too heavy or too many polygons (optimize, compress, LODs), broken normals, scale or origin, materials lost on glTF export, conversion between GLB, FBX and USDZ, texturing, rigging for animation, animating it (walk and idle cycles, text-to-motion, looping clips, articulated props), or inspection. Drives Blender through a Blender MCP server (ahujasid's or the official Blender Lab one). Batch mode produces many consistent assets unattended. Kiln Studio (`/kiln studio`) opens the project's models in the browser, where the user reviews them and pins notes for Claude to act on.
references/setup-install.md
View on GitHub# Setup — Local Installation Guide
**Never required.** kiln's default is scripted modeling, with no AI model; when the
user picks AI, a free Space comes first (`ai-generation.md`). Install only for offline
work. **Hunyuan3D-2's licence, below, does not apply in the EU, the UK or South Korea**
(first line of its `LICENSE`): show that and get a yes before installing. The
measured MIT alternative, TRELLIS.2 on Apple Silicon, is in `ai-generation.md`.
## Model Selection
```
Choose model storage location:
Default: ~/.hunyuan3d/models/
Custom: [enter path]
Available models:
1. hunyuan3d-dit-v2-mini (0.6B params, ~6 GB VRAM) — balanced quality
2. hunyuan3d-dit-v2-mini-fast (0.6B params, ~6 GB VRAM) — faster, slightly lower quality
3. hunyuan3d-dit-v2-mini-turbo (0.6B params, ~6 GB VRAM) — fastest, preview quality
Which models to download? (1,2,3 or "all")
```
## Installation Commands (cross-platform)
```bash
# Clone repo
git clone https://github.com/Tencent/Hunyuan3D-2.git {models_path}/Hunyuan3D-2
cd {models_path}/Hunyuan3D-2
# Install dependencies
# A bare pip3 fails on any PEP 668 Python (Homebrew, most Linux distros).
python3 -m venv {models_path}/venv
{models_path}/venv/bin/pip install -r requirements.txt
{models_path}/venv/bin/pip install -e .
# Download model weights (via huggingface_hub)
python3 -c "
from huggingface_hub import snapshot_download
# Run with {models_path}/venv/bin/python, not the system python3.
snapshot_download('tencent/Hunyuan3D-2mini', local_dir='{models_path}/Hunyuan3D-2mini')
"
# (CUDA only) Compile texture generation extensions
# Skip on Mac/no-CUDA — texture will be handled by skill's TEXTURING phase
cd hy3dgen/texgen/custom_rasterizer && python3 setup.py install && cd ../../..
cd hy3dgen/texgen/differentiable_renderer && bash compile_mesh_painter.sh && cd ../../..
```
## Windows-specific Notes
- Use backslash paths or forward slashes in Python
- May need Visual Studio Build Tools for CUDA extension compilation
- `bash compile_mesh_painter.sh` → use Git Bash or WSL
## Post-install Validation
```python
python3 -c "
import torch
from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
device = 'cuda' if torch.cuda.is_available() else ('mps' if torch.backends.mps.is_available() else 'cpu')
print(f'Device: {device}')
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained(
'{models_path}/Hunyuan3D-2mini',
subfolder='hunyuan3d-dit-v2-mini-turbo',
use_safetensors=True,
device=device
)
print('✅ Shape generation ready')
"
```
**If validation passes:** "✅ Local backend ready. Shape generation on {device}."
**If CUDA not available:** "⚠️ No NVIDIA GPU detected. Shape generation will use {mps/cpu} (slower). Texture generation unavailable locally — skill will texture via Blender (phase TEXTURING)."
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: 472k | 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 |