StableGen: AI-Powered 3D Generation & Texturing in Blender ✨

Create 3D assets from images and prompts, then texture and refine them - all inside Blender.

StableGen is an open-source Blender addon that brings generative AI into your 3D workflow. Generate fully textured 3D meshes from a single image or text prompt via TRELLIS.2, then texture and refine them - or any existing model - using SDXL, FLUX.1-dev, or Qwen Image Edit through a flexible ComfyUI backend.

---

<details> <summary><strong>Table of Contents</strong></summary>

• 🌟 Key Features
• 🚀 Showcase Gallery
• 🛠️ How It Works
• 💻 System Requirements
• ⚙️ Installation
• 🚀 Quick Start Guide
  • Texturing an Existing Model
  • Generating a 3D Model with TRELLIS.2
• 📖 Usage & Parameters Overview
• 📁 Output Directory Structure
• 🤔 Troubleshooting
• 🤝 Contributing
• 📜 License
• 🙏 Acknowledgements
• 💡 List of planned features
• 📧 Contact

</details>

---

🌟 Key Features

StableGen brings AI-powered 3D generation and texturing directly into Blender:

• 🧊 TRELLIS.2: Image & Prompt to 3D:
  • Generate fully textured 3D meshes from a single reference image or text prompt using Microsoft's TRELLIS.2 (4B-parameter model).
  • Multiple resolution modes: 512, 1024, 1024 Cascade (recommended), and 1536 Cascade for maximum geometric detail.
  • Flexible texture pipeline: Use TRELLIS.2's native PBR textures, or automatically texture the generated mesh with SDXL, FLUX.1-dev, or Qwen Image Edit for higher-quality diffusion textures.
  • Preview Gallery: Generate multiple candidate images with different seeds and pick the best before committing to 3D generation.
  • Smart mesh handling: Auto-recovery from mesh corruption, configurable decimation/remeshing, import scaling, and studio lighting setup.
  • VRAM-conscious: disk offloading, configurable attention backend
  • Powered by ComfyUI-TRELLIS2 (installable via installer.py).
• 🌍 Scene-Wide Multi-Mesh Texturing:
  • Don't just texture one mesh at a time! StableGen is designed to apply textures to all mesh objects in your scene simultaneously from your defined camera viewpoints. Alternatively, you can choose to texture only selected objects.
  • Achieve a cohesive look across entire environments or collections of assets in a single generation pass.
  • Ideal for concept art, look development for complex scenes, and batch-texturing asset libraries.
• 🎨 Multi-View Consistency:
  • Sequential Mode: Generates textures viewpoint by viewpoint on each mesh, using inpainting and visibility masks for high consistency across complex surfaces.
  • Grid Mode: Processes multiple viewpoints for all meshes simultaneously for faster previews. Includes an optional refinement pass.
  • Sophisticated weighted blending ensures smooth transitions between views.
• 📷 Advanced Camera Placement:
  • 7 placement strategies: Orbit Ring, Fan Arc, Hemisphere, PCA-Axis, Normal-Weighted K-means, Greedy Occlusion Coverage, and Interactive Visibility-Weighted placement.
  • Per-camera optimal aspect ratios - each camera gets its own resolution computed from the mesh's silhouette, so no pixels are wasted on letterboxing.
  • Unlimited cameras - no more 8-camera limit.
  • Camera generation order - drag-and-drop reorder list with 6 preset strategies to control the processing order in Sequential mode.
  • Camera cloning, mirroring, and floating viewport prompt labels.
• 🎯 Local Edit Mode:
  • Point cameras at specific areas to modify - new texture blends seamlessly over the original using angle-based and vignette-based feathering.
  • Separate angle ramp and silhouette edge feathering controls for precise blending.
  • Works with all architectures (SDXL, Flux, Qwen Image Edit).
• 📐 Precise Geometric Control with ControlNet:
  • Leverage multiple ControlNet units (Depth, Canny, Normal) simultaneously to ensure generated textures respect your model's geometry.
  • Fine-tune strength, start/end steps for each ControlNet unit.
  • Supports custom ControlNet model mapping.
• 🖌️ Powerful Style Guidance with IPAdapter:
  • Use external reference images to guide the style, mood, and content of your textures with IPAdapter.
  • Employ IPAdapter without an reference image for enhanced consistency in multi-view generation modes.
  • Control IPAdapter strength, weight type, and active steps.
• ⚙️ Flexible ComfyUI Backend:
  • Connects to your existing ComfyUI installation, allowing you to use your preferred SDXL checkpoints, custom LoRAs, and the new Qwen Image Edit workflow alongside experimental FLUX.1-dev support.
  • Offloads heavy computation to the ComfyUI server, keeping Blender mostly responsive.
• ✨ Advanced Inpainting & Refinement:
  • Refine Mode (Img2Img): Re-style, enhance, or add detail to existing textures (StableGen generated or otherwise) using an image-to-image process.
  • Local Edit Mode: Selectively modify specific areas while preserving the rest, with independent angle and vignette feathering controls.
  • UV Inpaint Mode: Intelligently fills untextured areas directly on your model's UV map using surrounding texture context.
  • Color Matching: Match each generated view's colors to the current texture before blending, using multiple algorithms (MKL, Reinhard, Histogram, MVGD).
• 🛠️ Integrated Workflow Tools:
  • Camera Setup: Quickly add and arrange multiple cameras with 7 placement strategies, per-camera aspect ratios, interactive occlusion preview, and customizable generation order.
  • View-Specific Prompts: Assign unique text prompts to individual camera viewpoints for targeted details.
  • Texture Baking: Convert complex procedural StableGen materials into standard UV image textures. "Flatten for Refine" option lets you bake and continue editing.
  • Debug Tools: Visualize projection coverage, UV alignment, and weight blending without running AI generation.
  • HDRI Setup, Modifier Application, Curve Conversion, GIF/MP4 Export & Reproject.**
• 📋 Preset System:
  • Get started quickly with built-in presets for common scenarios (e.g., "Default", "Characters", "Quick Draft").
  • Save and manage your own custom parameter configurations for repeatable workflows.

---

🚀 Showcase Gallery

<details open> <summary>See what StableGen can do!</summary>

_{Tip: Refresh the page to synchronize all GIF animations.}

---

Showcase 1: Text-to-3D (SDXL)

Assets generated entirely from a text prompt using the TRELLIS.2 pipeline with SDXL-based texturing.

| Dragon | Wizard | Hut | | :------: | :------: | :------: | | <img src="docs/img/trellis2/sdxl_dragon.gif" alt="Fantasy dragon" width="200"> | <img src="docs/img/trellis2/sdxl_wizard.gif" alt="Wizard character" width="200"> | <img src="docs/img/trellis2/sdxl_hut.gif" alt="Hut" width="200"> | | Telescope | Robot | Cyber Ninja | | <img src="docs/img/trellis2/sdxl_telescope.gif" alt="Telescope" width="200"> | <img src="docs/img/trellis2/sdxl_robot.gif" alt="Robot" width="200"> | <img src="docs/img/trellis2/sdxl_cyber_ninja.gif" alt="Cyber Ninja" width="200"> |

<details> <summary>Prompts used</summary>

1. Dragon: "fantasy dragon"
2. Wizard: "wizard character, intricate embroidered purple and gold robes, pointed hat, wooden staff with glowing crystal, leather belt with pouches, fantasy character concept art, 4k"
3. Hut: "house, small house, cozy, wooden, hut"
4. Telescope: "antique brass telescope, tarnished patina with bright spots from handling, leather grip wrap, extended sections, mahogany tripod, product photography, 4k"
5. Robot: "giant robot, mecha, cyberpunk style, sci-fi, white body, intricate details, neon accents"
6. Cyber Ninja: "full body character, neutral pose, cyber-ninja, futuristic assassin, matte black carbon fiber stealth suit, hexagonal weave pattern, faceless helmet, glowing red neon visor slit, metallic silver shoulder armor, cyberpunk aesthetic, high contrast materials, unreal engine 5 render"

</details>

Showcase 2: Text-to-3D (Qwen)

Text-to-3D via TRELLIS.2 with Qwen Image Edit texturing - well-suited for stylized objects and crisp details.

| Barrel | Chest | Crate | | :------: | :------: | :------: | | <img src="docs/img/trellis2/qwen_barrel.gif" alt="Barrel" width="200"> | <img src="docs/img/trellis2/qwen_chest.gif" alt="Chest" width="200"> | <img src="docs/img/trellis2/qwen_crate.gif" alt="Crate" width="200"> | | Obelisk | Robot | Tree Stump | | <img src="docs/img/trellis2/qwen_obelisk.gif" alt="Obelisk" width="200"> | <img src="docs/img/trellis2/qwen_robot.gif" alt="Robot" width="200"> | <img src="docs/img/trellis2/qwen_tree_stump.gif" alt="Tree Stump" width="200"> |

<details> <summary>Prompts used</summary>

1. Barrel: *"A chunky, stylized wooden barrel bound by thick, oversized iron hoops. The wo