Z-Image-Engineer-Blender

The world's first Blender-specialized prompt engineering model

Fine-tuned on 2,759 production Blender prompts from the Llammy addon ecosystem.

---

🎯 Model Overview

Z-Image-Engineer-Blender is a Qwen2.5-Coder-3B model fine-tuned specifically for Blender 3D workflows. This model provides expert guidance on:

• 3D modeling and sculpting
• Materials and shaders (Principled BSDF, node setups)
• Geometry Nodes and procedural workflows
• Python scripting for Blender automation
• Rendering (Cycles, EEVEE)
• Animation and rigging
• Blender version compatibility (2.79 - 5.2+)

Created by: Eternal Path Media (永恒之路) Base Model: Qwen2.5-Coder-3B-Instruct-4bit Training Method: LoRA fine-tuning with MLX Format: GGUF Q5_K_M (2.1 GB)

---

📊 Training Details

• Dataset: 2,759 Blender-specific prompt/response pairs
• Source: Production data from Llammy Blender addon (19,405+ interactions)
• Training Iterations: 1,000
• LoRA Rank: 16 layers
• Final Training Loss: 0.219
• Final Validation Loss: 0.243
• Framework: MLX (Apple Silicon optimized)

---

🚀 Quick Start

Using with Ollama

# Import the model
ollama create bartendr604/z-image-engineer-blender -f Modelfile

# Run interactively
ollama run bartendr604/z-image-engineer-blender

# Example prompt
ollama run bartendr604/z-image-engineer-blender "How do I create a glass material with realistic caustics?"

Using with llama.cpp

./main -m z-image-engineer-blender-Q5_K_M.gguf -p "How do I set up geometry nodes for scattering?"

---

💡 Example Usage

Geometry Nodes Workflow

Prompt:

How do I set up geometry nodes for scattering instances on a surface?

Response:

To set up Geometry Nodes for scattering instances on a surface in Blender,
follow these steps:

### Step-by-Step Guide: Setting Up Geometry Nodes for Scattering Instances

#### Material Node Setup

1. **Create or Select your object with instances:**
   - Open Blender and create a new scene or open an existing one.
   - Create the base geometry (e.g., cylinder) that will be used as instances.

2. **Assign Material to Object:**
   - Select your main object (the one with instances).
   - Go to the "Object" tab in the Properties panel...

[Full detailed step-by-step instructions with proper Blender terminology]

Python Scripting

Prompt:

Write a Python script to batch rename all selected objects

Response:

import bpy

# Get all selected objects
selected_objects = bpy.context.selected_objects

# Define the new base name
base_name = "Object"

# Rename each object with an index
for i, obj in enumerate(selected_objects):
    obj.name = f"{base_name}_{i:03d}"

print(f"Renamed {len(selected_objects)} objects")

Material Creation

Prompt:

How do I create a metallic material with scratches?

Response:

[Detailed node setup with Principled BSDF, roughness maps,
normal maps, and procedural texture techniques]

---

🎨 Use Cases

• Blender addon integration - Power AI assistants like Llammy
• Tutorial generation - Create step-by-step Blender guides
• Workflow automation - Generate Python scripts for repetitive tasks
• Troubleshooting - Debug scene setup issues
• Version compatibility - Get version-aware advice (2.79 - 5.2+)

---

📈 Performance

• Tokens per second: ~90-110 (on Apple M-series chips)
• Context length: 8,192 tokens
• Model size: 2.1 GB (Q5_K_M quantization)
• Memory usage: ~4-5 GB during inference

---

🔧 Technical Specifications

Specification	Value
Architecture	Qwen2.5-Coder-3B
Parameters	~3 billion
Quantization	Q5_K_M (GGUF)
Context Window	8,192 tokens
Training Data	2,759 Blender prompts
LoRA Layers	16
Training Framework	MLX (Apple Silicon)

---

📝 Modelfile (Ollama)

FROM ./z-image-engineer-blender-Q5_K_M.gguf

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 8192

SYSTEM """You are Z-Image-Engineer-Blender, a world-class Blender 3D specialist trained on production data from the Llammy addon. You provide expert guidance on Blender workflows, Python scripting, materials, geometry nodes, PBR rendering, and version-specific features (2.79-5.2). You understand Blender's evolution and provide compatibility-aware solutions. Created by Eternal Path Media (永恒之路)."""

---

🌟 Related Models

• llama-sentient-blender - Llama 3.2-based variant with friendly personality
• llammyblend-enhanced - Qwen Coder variant optimized for scripts

---

📚 Dataset

This model was trained on the blender-prompt-dataset containing 2,759 unique Blender-specific prompts extracted from the Llammy production ecosystem.

---

📄 License

MIT License - Free for commercial and personal use

---

🙏 Acknowledgments

• Llammy Blender Addon - Production data source
• Apple MLX - Training framework
• Qwen Team - Base model
• llama.cpp - GGUF conversion tools

---

🔗 Links

• GitHub: Eternal Path Media
• Dataset: blender-prompt-dataset
• Llammy Addon: Blender AI Assistant

---

📧 Contact

For questions, issues, or collaborations, reach out via GitHub or HuggingFace discussions.

永恒之路 (Eternal Path Media) - Bringing AI to Blender 🌟