carson-katri/dream-textures

Stable Diffusion built-in to Blender

What it solves

Dream Textures integrates Stable Diffusion directly into Blender, allowing 3D artists to generate textures, concept art, and background assets using text prompts without leaving their 3D workspace. It eliminates the need to switch between external AI image generators and manually importing assets into a Blender scene.

How it works

The add-on runs Stable Diffusion models locally on the user's machine (supporting CUDA and Apple Silicon GPUs) or via cloud processing through DreamStudio. It provides a set of tools for image generation, seamless tiling, and AI upscaling. It also features a "Project Dream Texture" tool that uses depth-to-image to texture entire scenes and a node system for creating complex effects through render passes.

Who it’s for

3D artists, environment designers, and concept artists using Blender who want to leverage generative AI to speed up their texturing and asset creation workflow.

Highlights

  • Seamless Textures: Create perfectly tiling textures with no visible seams.
  • Texture Projection: Use depth-to-image to apply AI-generated textures to 3D models and scenes.
  • Inpainting and Outpainting: Fix images or extend their boundaries automatically.
  • Local Execution: Run models on your own hardware to avoid service slowdowns.
  • AI Upscaling: Increase the resolution of generated images by 4x.
  • Node-based Workflow: Use a render engine node system to re-style animations and create effects.

Related

  • Project
    LibrePhotos/librephotos

    LibrePhotos is a self‑hosted photo‑management server that automatically adds AI‑generated metadata (faces, objects, captions) and offers semantic search, map view, and multi‑user albums. It ships as Docker containers with a Django REST backend, React web UI, and optional React‑Native Android client, using ONNX‑run models for all computer‑vision tasks.

  • Project
    MochiDiffusion/MochiDiffusion

    A native macOS application for running Stable Diffusion and FLUX.2 Klein locally on Apple Silicon, optimized for high performance and low memory usage via Core ML.

  • Project
    Nutlope/logocreator

    LogoCreator is an open‑source web app that generates brand‑ready logos using the FLUX‑2 image model via Together AI. Built with Next.js, TypeScript, Radix, and Tailwind, it runs without an account—just a Together AI key. Features include instant generation, FLUX‑1 edits, PNG/SVG export, optional rate‑limiting and auth, and a history dashboard. The repo provides clear setup steps and lists future tasks such as size selection, cost preview, reference‑logo uploads, and a showcase of redesigned famous logos.

  • Project
    NVlabs/Sana

    SANA is an open‑source, efficiency‑oriented diffusion codebase from NVIDIA for high‑resolution image and video generation. It includes multiple model families (SANA, SANA‑1.5, SANA‑Sprint, SANA‑Video/Video 2.0, SANA‑WM, SANA‑Streaming) and a reinforcement‑learning wrapper (Sol‑RL). Key tricks are linear attention, a 32× compression auto‑encoder (DC‑AE), decoder‑only text encoders, and sCM distillation, enabling 4K image generation and minute‑long 720p video generation with far less GPU cost than comparable models. The repo provides training/inference scripts, pretrained checkpoints on Hugging Face, Diffusers integration, ComfyUI nodes, and demos. Licensed Apache 2.0.