Repolode
Submit
carson-katri

carson-katri/dream-textures

A Blender add-on that generates textures, concept art and images from text prompts using Stable Diffusion, running locally on your machine.

View on GitHub
Stars
8,223
Forks
437
Open issues
15
Last commit
last month

What is it?

Dream Textures brings Stable Diffusion into Blender as an add-on. You can generate textures, concept art and background assets from a text prompt, then apply the results directly in your scene.

Beyond plain generation, the add-on supports seamless tiling textures, depth-to-image texture projection for whole models and scenes, inpainting and outpainting of existing images, and 4x AI upscaling. It also provides a node system for the Cycles render pass, which can be used to restyle animations, and a history panel for recalling, exporting and importing past generations.

Models run on your own hardware, so iterating does not depend on an external service. The project is tested with CUDA and Apple Silicon GPUs, with more than 4GB of VRAM recommended; a cloud option via DreamStudio is offered for unsupported hardware.

Key features

  • 01Generate textures and concept art from text prompts inside Blender
  • 02Create seamless tiling textures
  • 03Project generated textures onto models and scenes using depth to image
  • 04Inpaint and outpaint existing images
  • 054x AI upscaling of low-resolution outputs
  • 06Browse, export and import generation history

Use cases

  • Creating tiling materials and textures for 3D models without leaving Blender
  • Generating concept art or background assets during scene blocking
  • Restyling rendered animation frames with the Cycles render pass
  • Running image generation locally on a machine with a supported GPU

Quick start

  1. 1

    Download the latest release from the releases page

  2. 2

    Install the downloaded add-on in Blender and follow the release instructions

  3. 3

    On macOS, if dependencies are blocked by quarantine, clear the quarantine flag

    xattr -r -d com.apple.quarantine ~/Library/Application\ Support/Blender/3.3/scripts/addons/dream_textures/.python_dependencies

Things to know

  • Needs a GPU with over 4GB of VRAM recommended, tested mainly with CUDA and Apple Silicon.
  • Runs Stable Diffusion locally, so large model downloads and setup are required.
  • Requires Blender; it is an add-on, not a standalone app.
  • Licensed under GPL-3.0, a copyleft license.

Topics

#stable-diffusion#blender#blender-addon#image-generation#texture-generation#ai-art#ai

FAQ

What is dream-textures?
A Blender add-on that generates textures, concept art and images from text prompts using Stable Diffusion, running locally on your machine. Dream Textures brings Stable Diffusion into Blender as an add-on. You can generate textures, concept art and background assets from a text prompt, then apply the results directly in your scene.
Is dream-textures free to use? What license does it have?
dream-textures is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
Is dream-textures still maintained?
Updated within 6 months. The last commit to dream-textures was on Sep 17, 2026.
What can I use dream-textures for?
Creating tiling materials and textures for 3D models without leaving Blender Generating concept art or background assets during scene blocking Restyling rendered animation frames with the Cycles render pass Running image generation locally on a machine with a supported GPU
How do I install dream-textures?
Download the latest release from the releases page Install the downloaded add-on in Blender and follow the release instructions On macOS, if dependencies are blocked by quarantine, clear the quarantine flag: xattr -r -d com.apple.quarantine ~/Library/Application\ Support/Blender/3.3/scripts/addons/dream_textures/.python_dependencies
Where can I get dream-textures?
The source code and installation instructions are on GitHub: https://github.com/carson-katri/dream-textures

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects