v0.4.8 - Multi-LoRA, Inpaint, Weight Caching, Variants

Multi-LoRA, Inpaint, Weight Caching, Variants

This update focuses on making Diffuse easier to use, more flexible, and faster to work with — especially when experimenting with models, LoRAs, and larger images.

What’s New

Inpaint & Outpaint

• Added Inpaint and Outpaint support
• Includes new views and pipeline support

Multi-LoRA Support

• Use multiple LoRAs at the same time
• LoRAs can be added, removed, or changed without restarting the pipeline

Model Variants

• Added support for Hugging Face model variants
• Easily add variants like fp16, bf16, and more

Improved Image Tiling

• Brand-new tiling system
• Faster and more memory-efficient
• Significantly improved image quality, especially at higher resolutions

Pipeline Refresh

• Pipelines (Text-to-Image, Image-to-Image, etc.) can now be changed without unloading model weights
• Reload LoRAs, ControlNets, Upscalers, and Extractors on the fly
• Faster iteration with fewer full reloads

Bug Fixes & Stability Improvements
Various fixes and internal cleanups to improve reliability during model loading and inference.

Full Changelog: v0.4.0...v0.4.8

---

Installation

1. Installer Version

1. Uninstall Diffuse vX.X.X
2. Download and run Diffuse_v0.4.8.exe
3. Follow the on-screen instructions

2. Standalone Version

1. Download and extract Diffuse_v0.4.8.zip
   A fast SSD with plenty of free space is recommended, as model downloads can be large.

2. Run Diffuse.exe

Diffuse will automatically:

• Install an isolated portable Python runtime
• Create the required virtual environment
• Download the selected model from Hugging Face

First-run notice

On first launch or when loading a model for the first time, setup may take several minutes while Python, dependencies, and model files are downloaded and initialized. This is expected behavior.

No manual Python setup is required.

Device Support

Supports CUDA and ROCM based devices

⚠️ Important (Beta Notice)

Diffuse is still in Beta, and during this phase some releases include large internal changes.

For this version, a full uninstall and reinstall is recommended to avoid upgrade issues.
Your downloaded models are not affected and can be kept.

Settings.json will be replaced during installation
If you have added custom environments, paths, or models, please back up your Settings.json file before upgrading.

These upgrade steps are temporary and expected during Beta. The goal is to stabilise updates and avoid full reinstalls for future releases.