Stable Diffusion web UI - AI Image Tools Tool

Overview

Stable Diffusion web UI (AUTOMATIC1111) is an open‑source Gradio-based front end for running and experimenting with Stable Diffusion models locally. It exposes the common generation modes (txt2img, img2img) plus inpainting, outpainting, tiled/loopback workflows, highres-fix, negative prompts, prompt editing and live previews. The UI saves generation parameters into image metadata, supports multiple samplers and upscalers, and provides convenience features such as prompt styles, prompt matrix, X/Y/Z plotting, and on-the-fly checkpoint swapping. Many extra tools — GFPGAN/CodeFormer/RealESRGAN, textual inversion training, and embedding management — are either built-in or available via the Extras/Extensions system. ([github.com](https://github.com/AUTOMATIC1111/stable-diffusion-webui)) Beyond the core UI, the project maintains a large extensions ecosystem (installable from the UI) and a local REST-style API (/sdapi/v1/*) for programmatic control. The repository is actively developed and widely used (see releases and extension index); common launch options support memory modes, xformers acceleration, and platform-specific optimizations. The codebase and packaging list precise Python/package version requirements in the repo. Because it is published under AGPL-3.0, the software itself is free to use, but generation costs (GPU, CPU, RAM, or cloud hosting) remain the user's responsibility. ([github.com](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Extensions?utm_source=openai))

GitHub Statistics

• Stars: 159,768
• Forks: 29,754
• Contributors: 428
• License: AGPL-3.0
• Primary Language: Python
• Last Updated: 2024-07-27T12:49:39Z
• Latest Release: v1.10.1

Key Features

• txt2img and img2img modes with sampler selection and highres-fix
• Mask-based inpainting and outpainting (canvas and script-driven workflows)
• Local REST API (/sdapi/v1) for programmatic generation and automation
• Embedding management and Textual Inversion training support
• Built-in Extras: GFPGAN/CodeFormer face restore and RealESRGAN upscaling
• Extension system with community plugins (ControlNet, LoRA, many scripts)
• Prompt tools: negative prompts, prompt matrix, styles, X/Y/Z plotting

Example Usage

Example (python):

import base64
import requests

# Example: send a txt2img request to a local AUTOMATIC1111 webui instance.
# Requires webui launched with the --api flag. See /sdapi/v1/docs in the running UI.

url = "http://127.0.0.1:7860/sdapi/v1/txt2img"
payload = {
    "prompt": "A fantasy landscape, dramatic lighting, 4k",
    "negative_prompt": "blurry, lowres",
    "steps": 20,
    "sampler_index": "Euler",
    "cfg_scale": 7.0,
    "width": 512,
    "height": 512,
    "batch_size": 1
}

r = requests.post(url, json=payload)
r.raise_for_status()
result = r.json()
# result["images"] is a list of base64-encoded PNG/JPEG images
if result.get("images"):
    img_b64 = result["images"][0]
    img_bytes = base64.b64decode(img_b64.split(",")[-1])
    with open("output.png", "wb") as f:
        f.write(img_bytes)
    print("Saved output.png")
else:
    print("No images returned; response:", result)

Pricing

Free, open-source software licensed under AGPL-3.0. No commercial licensing cost from the project; users pay for hardware, cloud GPU/hosting, or third‑party services used to run it. (See repository license and project README.)

Benchmarks

GitHub stars: ≈160k stars (repository front page) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui)

GitHub forks: ≈29.8k forks (repository front page) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui)

Open issues (approx.): ≈2.4k open issues (indicator on repo page) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui)

Commits (history): ≈7,689 commits on main branch (history counter) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui)

Latest release (tag): v1.10.1 (latest release tag shown in Releases list) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases)

Minimum GPU VRAM (reported): Runs on cards with as little as ~4 GB VRAM (community reports of smaller setups) (Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui)

Key Information

• Category: Image Tools
• Type: AI Image Tools Tool