dream-textures  by carson-katri

Blender add-on for Stable Diffusion integration

created 2 years ago
8,048 stars

Top 6.5% on sourcepulse

GitHubView on GitHub
Project Summary

Dream Textures integrates Stable Diffusion directly into Blender, enabling artists and 3D modelers to generate textures, concept art, and scene assets via text prompts. It offers features like seamless tiling, depth-to-image projection for scene texturing, animation re-styling, and AI upscaling, streamlining the creative workflow within a familiar 3D environment.

How It Works

The add-on leverages Stable Diffusion models, allowing users to run them locally on their machine for faster iteration without service slowdowns. It integrates with Blender's Cycles render engine via a node system, enabling complex AI-driven material creation and effects. Key features include inpainting/outpainting for texture refinement and expansion, and a history recall system for managing generations.

Quick Start & Requirements

  • Install by downloading the latest release and following instructions.
  • Requires Blender.
  • Tested with CUDA and Apple Silicon GPUs; over 4GB VRAM recommended.
  • macOS users may need to run xattr -r -d com.apple.quarantine ~/Library/Application\ Support/Blender/3.3/scripts/addons/dream_textures/.python_dependencies in Terminal to resolve dependency issues.
  • Video tutorial available: https://youtu.be/kEcr8cNmqZk

Highlighted Details

  • Seamless texture generation.
  • Depth-to-image projection for scene texturing.
  • AI upscaling (4x).
  • Inpainting/Outpainting capabilities.

Maintenance & Community

  • Active development and feedback accepted via GitHub issues.
  • Discord server available for community support and common issues.

Licensing & Compatibility

  • License not explicitly stated in the README.
  • Compatible with CUDA and Apple Silicon GPUs.

Limitations & Caveats

The README mentions potential macOS quarantine issues with dependencies. It recommends over 4GB of VRAM for optimal performance. Cloud processing via DreamStudio is an option for unsupported hardware.

Health Check
Last commit

11 months ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
2
Star History
87 stars in the last 90 days

Explore Similar Projects

Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Georgios Konstantopoulos Georgios Konstantopoulos(CTO, General Partner at Paradigm), and
2 more.

mflux by filipstrand

0.7%
2k
MLX port of FLUX for local image generation on Macs
created 11 months ago
updated 10 hours ago
Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Lyumin Zhang Lyumin Zhang(Author of ControlNet), and
2 more.

Fooocus by lllyasviel

0.2%
46k
Image generator for streamlined prompting and generation using SDXL
created 2 years ago
updated 6 months ago
Feedback? Help us improve.