CalamitousFelicitousness
6ea2c50d5d
The analyzer only mapped plain-lora groups, so a file carrying no plain lora (a pure lokr, for example) analyzed zero modules and fell through to a 1.0 default: it reported perfect fidelity for exactly the files that degrade most. Measured on the shipped krea 2 uint4 checkpoint, those files land between 0.04 and 0.34. Every targeted module is now rebuilt with the loader's own module class and its delta read from the production calc_updown, so lokr, loha, oft, full, ia3, glora, norm and the dora / dense-bias / diff_b variants are measured as they apply; factor-path eligibility is decided by calling the loader's own predicate. Modules carrying several families sum their deltas the way the loader stacks them, and a family the tool cannot rebuild is reported instead of counting as clean. - report per-module applied fidelity (1.0 on the factor path, measured rho on the requantize path) as a median and an energy-weighted mean - add --dtype bf16 to measure the unquantized reference rather than assert it - drop the per-module empty_cache: it cost 16ms per module against 1ms of reuse, and the caching allocator already reuses the buffers - keep shard handles open across modules
SD.Next: All-in-one WebUI
SD.Next is a state-of-the-art, open-source server application and web interface (WebUI) for AI image and video generation, built on Stable Diffusion and supporting dozens of advanced models. Create, refine, caption, upscale and process images and videos with a modern, cross-platform application — perfect for artists, researchers, and AI enthusiasts.
Table of contents
- Documentation
- Why SD.Next?
- Screenshots
- Supported Workflows
- Supported AI Models
- Supported Platforms & Hardware
- Getting started
- Community and Support
- Credits
- Development and Contributing
Why SD.Next?
SD.Next is feature-rich open-source AI art generation platform with a focus on performance, flexibility, and user experience.
In addition to supporting all popular workflows, a wide range of platforms and models, SD.Next includes many features not found in other WebUIs, such as:
- Support for many Diffusion models!
- Automatic model download: simply select a model from the list of reference models and it will be downloaded and ready to use
Or download and add your own models and they will be automatically detected and available in the UI - SDNQ: State-of-the-Art model quantization engine Use pre-quantized or run with quantization on-the-fly for up to 4x VRAM reduction with no or minimal quality and performance impact
- Balanced Offload: Dynamically balance CPU and GPU memory to run larger models on limited hardware
- Caption and Enhance with 25+ built-in LLM and VLM models, OpenCLiP models, Tagger with WaifuDiffusion and DeepDanbooru models
- Image Processing with full image correction color-grading suite of tools
- Multi-platform!
Platform specific auto-detection and tuning performed on install - Fully Localized to ~15 languages and with support for many UI themes!
- Desktop and mobile interfaces
- Built in installer with automatic updates and dependency management
Screenshots
Supported Workflows
- Generate with Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, etc.
- Edit with Detailer, HiRes/Refine, Image-Edit, Inpainting, Outpainting, etc.
- Enhance guidance with LoRA, ControlNet, IPAdapters, Prompt Enhance, etc.
- Process with Caption, Tag, Upscale, Interpolate, Colorize, Filter, etc.
- and many more with support for custom scripts and extensions
Supported AI Models
SD.Next supports broad range of models and its frequently updated with latest models
For full list, see supported models and model specs
Supported Platforms and Hardware
SD.Next is designed to run on a wide range of hardware and platforms, with optimizations for various GPU architectures with acceleration and support for CPU-only execution. Supported platforms include:
- nVidia GPUs using CUDA libraries on both Windows and Linux
- AMD GPUs using ROCm libraries on both Linux and Windows
- AMD GPUs on Windows using ZLUDA libraries
- Intel Arc GPUs using OneAPI with IPEX XPU libraries on both Windows and Linux
- Any CPU/GPU or device compatible with OpenVINO libraries on both Windows and Linux
- Any GPU compatible with DirectX on Windows using DirectML libraries
- Apple M1/M2 on OSX using built-in support in Torch with MPS optimizations
- ONNX/Olive
Plus Docker container recipes for: CUDA, ROCm, Intel IPEX and OpenVINO
Getting started
- Get started with SD.Next by following the installation instructions
- For more details, check out advanced installation guide
- List and explanation of command line arguments
- Install walkthrough video
Tip
And for platform specific information, check out
WSL | Intel Arc | DirectML | OpenVINO | ONNX & Olive | ZLUDA | AMD ROCm | MacOS | nVidia | Docker
Quick Start
git clone https://github.com/vladmandic/sdnext
cd sdnext
./webui.sh # Linux/Mac
webui.bat # Windows
webui.ps1 # PowerShell
Warning
If you run into issues, check out troubleshooting and debugging guides
Community and Support
If you're unsure how to use a feature, best place to start is Docs and if its not there,
check ChangeLog for when feature was first introduced as it will always have a short note on how to use it
And for any question, reach out on Discord or open an issue or discussion
Credits
Main credit goes to Automatic1111 WebUI for the original codebase
Development and Contributing
Please see Dev Home for details on how to contribute to this project