Welcome to SD.Next
Step 1: Installation
- Get started with SD.Next by following the Installation instructions
- For more details, check out Advanced installation guide and Update and Branches guide
- List and explanation of Command line arguments
- Install walkthrough Video
Note
And for platform specific information, check out
WSL | Intel Arc | DirectML | OpenVINO | ONNX & Olive | ZLUDA | AMD ROCm | MacOS | nVidia | Docker
Tip
If you run into issues, check out FAQ as well as Troubleshooting and Debugging guides
Step 2: Experiment
SD.Next supports broad range of models: Supported models and Model specs
A good starting point is to use built-in Reference model list which includes a variety of models that will be auto-downloaded and configured on first access.
Additionally, you can either download your own models or use built-in CivitAI and HuggingFace models downloader.
Tip
For additional model-specific information, check out
Stable Diffusion XL | Stable Diffusion 3.x | Stable Cascade | FLUX.1 | LCM
Step 3: Learn more
Guides and tutorials
- Getting started
- Overview of main features
- Frequently Asked Questions FAQ
- Prompting guide: what is the syntax and how to get the best results
- Networks interface overview and search
- What is LoRA and how to use it guide
- Control how-to, settings and technical: what is it and how to use it
- Detailer guide: how to use it
- Styles guide: how to use them
- Wildcards how-to: use them to your advantage
- Reprocess workflows: why and how to use them
- XYZ grid how-to: expertiment with different parameters
- Image processing overview: postprocess your existing images
- Intro to IP Adapters: image guidance
- Work with models: validate, convert, download, etc.
- Supported Video models: recommendations and limitations
- Overview of built-in scripts that provide additional functionality
Advanced model handling
Some models may require additional access checks before they can be used: Gated access
Learn how to optimize your environemnt: Performance tuning
Learn how you can manage your resources better:
- Memory Offloading
includes performance notes for different offload options - Model Quantization
- Model Compression
Plus collection of Benchmarks to highlight what to expect using different compile and/or device settings: - Compile/device settings
User interface
- Changing look & feel using Themes
- List of Keyboard shortcuts
Behind-the-scenes
If you want to use SD.Next via API or via CLI, check out - Tools examples
If you want to understand more how Stable Diffusion works
- Diffusion Pipeline: How it Works
- List of Training Methods
And two available backend modes in SD.Next: Diffusers & Original
As well as an advanced Profiling how-to