DiffusedTexture: AI-Powered Texture Generation for Blender

DiffusedTexture is a Blender add-on that uses Stable Diffusion to create textures directly on 3D meshes.

Table of Contents

• DiffusedTexture: AI-Powered Texture Generation for Blender
  • Table of Contents
  • Examples
  • Features
  • Installation
  • Platform Runtime Notes
  • Usage
    • Additional Options
  • Troubleshooting
  • Development
  • Acknowledgements

Examples

Features

• AI-Driven Texture Creation: Generate diffuse textures directly on 3D models
• Modes for Different Workflows:
  • Text2Image Parallel: Create textures from text prompts, ensuring global consistency.
  • Image2Image Parallel: Generates textures from input textures, applied parallel across all views.
  • Image2Image Sequential: Sequentially adjusts textures across views, great for refinement.
• LoRA Integration: Uses LoRA conditioning for specific styles.
• IPAdapter Integration: Fit specific styles or objects with images for enhanced flexibility and control.

Installation

1. Download the .zip file of the latest release

2. Install the downloaded diffused_texture_addon-<version>.zip file in Blender as an Add-On.

   • Edit -> Preferences... -> Sidebar Add-ons -> Top right corner dropdown menu -> Install from Disk...

3. Install the dependencies by clicking the Install Dependencies button in the Add-On panel.

   • This will take a while as it installs all necessary packages, including PyTorch and diffusers.
   • The Dependency backend setting chooses which PyTorch wheels to install for the diffusion stack. It does not by itself guarantee that Blender can use the same backend for the Cycles render pass.

4. RESTART BLENDER! This is important to ensure all packages are correctly loaded.

5. (Optional) Download the necessary models by clicking the Download Models button in the Add-On panel.

   • If wanted, provide a custom HuggingFace Cache Path to install and/or load the checkpoints, else the default path is choosen.
   • Download necessary models (~10.6 GB total)
   • You can also run the add-on without downloading the models, but it will take longer to generate textures as they will be downloaded on-the-fly.
   • The models will be stored in the specified HuggingFace Cache Path or the default cache path.

Platform Runtime Notes

• DiffusedTexture now reports two separate platform decisions:
  • Dependency backend: which PyTorch wheels are installed for diffusion (cpu, CUDA, ROCm, or auto-detect).
  • Runtime capability: which Cycles render backend Blender can actually use for the render pass, plus which diffusion device PyTorch/diffusers can use at runtime.
• For Cycles renders, the add-on prefers OPTIX, CUDA, HIP, ONEAPI, and METAL, then falls back to CPU when no GPU backend is usable.
• This means a machine can install a non-NVIDIA diffusion backend and still render through Cycles on CPU if that is the only render path Blender exposes locally.

Usage

1. Load or create a 3D Model:
   • Import or create a .blend file containing the 3D model.
2. UV Unwrap the Model:
   • Apply a UV map (Smart UV Project works well).
3. Access the Add-On:
   • Open the DiffusedTexture panel in the N-panel (right-hand sidebar).
4. Set Up Texture Generation:
   • Prompt & Negative Prompt: Describe the desired texture/object and what to avoid.
   • Guidance Scale: Adjust creativity vs. fidelity.
   • Denoise Strength: Default to 1.0 for Text2Image.
5. Adjust Advanced Options:
   • Mesh Complexity:
     • Low: Depth ControlNet only.
     • Medium: Adds Canny ControlNet.
     • High: Adds Normalmap ControlNet for maximum detail.
   • Cameras: Use more viewpoints for better texture blending.
   • Texture & Render Resolution: Ensure render resolution is at least 2x texture resolution.
6. Generate Texture:
   • Click Start Texture Generation. Monitor progress in the system console.

Additional Options

• LoRA Models: Add one or multiple LoRA models to match specific results.
• IPAdapter: Supply the desired "look" as an image instead of a text prompt.
• SDXL: Use the more advanced SDXL model for higher quality textures.

Troubleshooting

• Add-On Not Visible: Ensure it’s enabled in Edit > Preferences > Add-ons.
• Blender Freezes: Open the system console to track progress during long tasks.
• Permission Issues: Specify a valid output path.
• Out of GPU Memory:
  • Reduce camera count.
  • Close other GPU-intensive applications.
• Platform Confusion: Check the Current Runtime Capability box in the add-on preferences. It shows the installed diffusion backend, the active Cycles render path, and whether texture generation is currently ready.
• Crashes: Restart Blender or your PC if crashes persist.

Development

• Default local dev environment: Python 3.13 with Blender 5.1+, installed via uv sync.
• The local uv configuration overrides the published bpy NumPy cap so the dev environment aligns with the CY2026 NumPy 2.3.x lane.
• Legacy Blender <5.1 / Python 3.11 compatibility is still covered by the installer matrix tests.
• Commit and hook setup: CONTRIBUTING.md
• Testing workflow and local check commands: documentation/TESTING.md
• Release automation and bootstrap instructions: documentation/RELEASING.md

Acknowledgements

• Inspired by Dream Textures by Carson Katri.
• Powered by:
  • Stable Diffusion
  • HuggingFace Diffusers
  • ControlNet
  • IPAdapter
• Influenced by research in TEXTure, Text2Tex, Paint3D, MatAtlas and EucliDreamer.