FastSD CPU :sparkles:

<div align="center"> <a href="https://trendshift.io/repositories/3957" target="_blank"><img src="https://trendshift.io/api/badge/repositories/3957" alt="rupeshs%2Ffastsdcpu | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </div>

FastSD CPU is a faster version of Stable Diffusion on CPU. Based on Latent Consistency Models and Adversarial Diffusion Distillation.

The following interfaces are available :

• Desktop GUI, basic text to image generation (Qt,faster)
• WebUI (Advanced features,Lora,controlnet etc)
• CLI (CommandLine Interface)

🚀 Using OpenVINO(SDXS-512-0.9), it took 0.82 seconds (820 milliseconds) to create a single 512x512 image on a Core i7-12700.

📰 News

• 2026-07-05 - Add bonsai image (1 bit) GGUF support, Flux2 Klein GGUF support
• 2026-06-21 - Added FLUX.2-klein-4B support(OpenVINO), image editing support, photo restoration, colorization (2 to 4 steps)
• 2026-05-01 - Docker support, HF demo
• 2025-12-22 - FastSD engine integrated into Intel's OpenVINO™ AI Plugins for GIMP
• 2025-05-17 - Added SANA Sprint(OpenVINO) support,Tiny AutoEncoder 1.3(Mocha Croissant) support
• 2025-04-20 - Added MCP server support,faster uv based installation,Claude desktop, Open WebUI support
• 2024-11-03 - Added Intel Core Ultra Series 2 (Lunar Lake) NPU support
• 2024-10-02 - Added GGUF diffusion model(Flux) support
• 2024-09-03 – Added Intel AI PC GPU, NPU support 🚀

Table of Contents 👇

• Supported Platforms
• Dependencies
• Memory requirements
• Features
• Architecture
• Benchmarks
• OpenVINO Support
• Installation
• Image Editing support
• Real-time text to image (EXPERIMENTAL)
• Models
• How to use Lora models
• How to use controlnet
• Docker support
• Android + Termux
• Raspberry Pi 4
• API Support
• GGUF support (Flux)
• AI PC Support - OpenVINO
• MCP Server Support
• Open WebUI Support
• ComfyUI support
• GIMP Plugin
• License
• Contributors

Supported platforms⚡️

FastSD CPU works on the following platforms:

• Windows
• Linux
• Mac
• Android + Termux
• Raspberry PI 4

Dependencies 📦

• Python 3.10 or higher
• uv - fast Python package and project manager

Memory requirements

Minimum system RAM requirement for FastSD CPU.

Model (LCM,OpenVINO): SD Turbo, 1 step, 512 x 512

Model (LCM-LoRA): Dreamshaper v8, 3 step, 512 x 512

| Mode | Min RAM | | --------------------- | ------------- | | LCM | 2 GB | | LCM-LoRA | 4 GB | | OpenVINO(Flux2) | 8 GB | | OpenVINO | 11 GB |

If we enable Tiny decoder(TAESD) we can save some memory(2GB approx) for example in OpenVINO mode memory usage will become 9GB.

:exclamation: Please note that guidance scale >1 increases RAM usage and slow inference speed.

Features ✨

• Desktop GUI, web UI and CLI
• Supports 256,512,768,1024 image sizes
• Supports Windows,Linux,Mac
• Saves images and diffusion setting used to generate the image
• Settings to control,steps,guidance and seed
• Added safety checker setting
• Maximum inference steps increased to 25
• Added OpenVINO support
• Fixed OpenVINO image reproducibility issue
• Fixed OpenVINO high RAM usage,thanks deinferno
• Added multiple image generation support
• Application settings
• Added Tiny Auto Encoder for SD (TAESD) support, 1.4x speed boost (Fast,moderate quality)
• Safety checker disabled by default
• Added SDXL,SSD1B - 1B LCM models
• Added LCM-LoRA support, works well for fine-tuned Stable Diffusion model 1.5 or SDXL models
• Added negative prompt support in LCM-LoRA mode
• LCM-LoRA models can be configured using text configuration file
• Added support for custom models for OpenVINO (LCM-LoRA baked)
• OpenVINO models now supports negative prompt (Set guidance >1.0)
• Real-time inference support,generates images while you type (experimental)
• Fast 2,3 steps inference
• Lcm-Lora fused models for faster inference
• Supports integrated GPU(iGPU) using OpenVINO (export DEVICE=GPU)
• 5.7x speed using OpenVINO(steps: 2,tiny autoencoder)
• Image to Image support (Use Web UI)
• OpenVINO image to image support
• Fast 1 step inference (SDXL Turbo)
• Added SD Turbo support
• Added image to image support for Turbo models (Pytorch and OpenVINO)
• Added image variations support
• Added 2x upscaler (EDSR and Tiled SD upscale (experimental)),thanks monstruosoft for SD upscale
• Works on Android + Termux + PRoot
• Added interactive CLI,thanks monstruosoft
• Added basic lora support to CLI and WebUI
• ONNX EDSR 2x upscale
• Add SDXL-Lightning support
• Add SDXL-Lightning OpenVINO support (int8)
• Add multilora support,thanks monstruosoft
• Add basic ControlNet v1.1 support(LCM-LoRA mode),thanks monstruosoft
• Add ControlNet annotators(Canny,Depth,LineArt,MLSD,NormalBAE,Pose,SoftEdge,Shuffle)
• Add SDXS-512 0.9 support
• Add SDXS-512 0.9 OpenVINO,fast 1 step inference (0.8 seconds to generate 512x512 image)
• Default model changed to SDXS-512-0.9
• Faster realtime image generation
• Add NPU device check
• Revert default model to SDTurbo
• Update realtime UI
• Add hypersd support
• 1 step fast inference support for SDXL and SD1.5
• Experimental support for single file Safetensors SD 1.5/SDXL models(Civitai models), simply add local model path to configs/stable-diffusion-models.txt file.
• Add REST API support
• Add Aura SR (4x)/GigaGAN based upscaler support
• Add Aura SR v2 upscaler support
• Add FLUX.1 schnell OpenVINO int 4 support
• Add CLIP skip support
• Add token merging support
• Add Intel AI PC support
• AI PC NPU(Power efficient inference using OpenVINO) supports, text to image ,image to image and image variations support
• Add TAEF1 (Tiny autoencoder for FLUX.1) openvino support
• Add Image to Image and Image Variations Qt GUI support,thanks monstruosoft
• Add single file SDXL safetensor file support,thanks monstruosoft
• Add FLUX.2-klein-4B OpenVINO support
• Add image editing support
• Add bonsai image (1 bit) GGUF support, Flux 2 Klein GGUF model support

Architecture

FastSDCPU follows a loosely coupled architecture focusing on maintainability and usability.

Key Design Principles

Separation of Concerns: The core diffusion pipelines (Pytorch, OpenVINO, GGUF) are decoupled from the user interfaces.

Interface Flexibility: A unified underlying engine powers multiple frontend experiences seamlessly, including the Desktop GUI (Qt), the Advanced WebUI, and the Command Line Interface (CLI).

Extensibility: The modular setup allows easy integration of new features, such as the MCP server protocol and custom third-party plugins like GIMP.

<a id="fast-inference-benchmarks"></a>

Fast Inference Benchmarks

🚀 Fast 1 step inference with Hyper-SD

Stable diffuion 1.5

Works with LCM-LoRA mode. Fast 1 step inference supported on runwayml/stable-diffusion-v1-5 model,select rupeshs/hypersd-sd1-5-1-step-lora lcm_lora model from the settings.

Stable diffuion XL

Works with LCM and LCM-OpenVINO mode.

• Hyper-SD SDXL 1 step - rupeshs/hyper-sd-sdxl-1-step

• Hyper-SD SDXL 1 step OpenVINO - rupeshs/hyper-sd-sdxl-1-step-openvino-int8

Inference Speed

Tested on Core i7-12700 to generate 768x768 image(1 step).

| Diffusion Pipeline | Latency | | --------------------- | ------------- | | Pytorch | 19s | | OpenVINO | 13s | | OpenVINO + TAESDXL | 6.3s |

Fastest 1 step inference (SDXS-512-0.9)

:exclamation:This is an experimental model, only text to image workflow is supported.

Inference Speed

Tested on Core i7-12700 to generate 512x512 image(1 step).

SDXS-512-0.9

| Diffusion Pipeline | Latency | | --------------------- | ------------- | | Pytorch | 4.8s | | OpenVINO | 3.8s | | OpenVINO + TAESD | 0.82s |

🚀 Fast 1 step inference (SD/SDXL Turbo - Adversarial Diffusion Distillation,ADD)

Added support for ultra fast 1 step inference using sdxl-turbo model

:exclamation: These SD turbo models are intended for research purpose only.

Inference Speed

Tested on Core i7-12700 to generate 512x512 image(1 step).

SD Turbo

| Diffusion Pipeline | Latency | | --------------------- | ------------- | | Pytorch | 7.8s | | Open