Categories
Machine Learning Creative Tools Stable Diffusion AI Image Generation GPU Computing ControlNet Generative AIStars
Forks
Watchers
Developer links
SD WebUI Forge
With 12,800 GitHub stars and backing from the same developer who created ControlNet, Stable Diffusion WebUI Forge replaces Automatic1111's inference backend with a dynamic GPU memory management system that runs SDXL 30-75% faster while consuming significantly less VRAM — enabling 1024x1024 generation on 6GB cards where A1111 requires 8GB or more. The Gradio 4 interface provides txt2img, img2img, inpainting, and outpainting workflows with a Forge Canvas supporting pressure-sensitive input from Wacom tablets and Microsoft Surface devices. Native Flux.1 model support loads Flux Dev and Schnell checkpoints using BitsandBytes NF4 and FP8 quantization for deployment on consumer GPUs without model splitting. Built-in ControlNet integration includes all preprocessors — Canny, Depth, Normal, OpenPose, MLSD, Scribble, Segmentation, Tile, and IP-Adapter — without requiring separate extension installation. The extension ecosystem maintains full compatibility with popular Automatic1111 extensions including Adetailer for face enhancement, After Detailer, Regional Prompter, and Dynamic Prompts. LoRA loading supports standard, LyCORIS, and DoRA formats with automatic weight detection. The API provides RESTful endpoints for txt2img, img2img, extra single/batch processing, and progress monitoring enabling headless batch generation. Deploy via one-click installer package, Python virtual environment, or Docker with NVIDIA GPU passthrough. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.
Benefits
- 30-75% Faster SDXL Generation
- Replaces Automatic1111's inference backend with optimized GPU memory management that runs SDXL at significantly higher speeds while reducing VRAM requirements by 2-4GB.
- Native Flux.1 Model Support
- Loads Flux Dev and Schnell checkpoints using BitsandBytes NF4 and FP8 quantization, enabling next-generation image generation on consumer GPUs without model splitting.
- Integrated ControlNet Suite
- Ships with all ControlNet preprocessors and models built-in, including Canny, Depth, OpenPose, Scribble, IP-Adapter, and Instant-ID without requiring separate extension installation.
- Full Extension Ecosystem
- Maintains compatibility with the entire Automatic1111 extension ecosystem including Adetailer, Regional Prompter, Dynamic Prompts, and hundreds of community-developed plugins without modification.
Features
- Dynamic Memory Management
- GPU memory system automatically manages model loading, unloading, and VRAM allocation enabling multiple ControlNet models and LoRAs simultaneously on limited hardware.
- Gradio 4 Canvas
- Inpainting and outpainting canvas with pressure-sensitive input from Wacom tablets, layered editing, and real-time preview of generation results.
- Multi-Model Inference
- Supports Stable Diffusion 1.5, 2.1, SDXL, Flux.1, and custom fine-tuned checkpoints with automatic model detection, LoRA stacking, and VAE switching.
- RESTful Generation API
- Provides txt2img, img2img, extra processing, and progress endpoints for programmatic batch generation and headless workflow automation.
- Preprocessor Pipeline
- Includes Canny, Depth MiDaS, Normal BAE, OpenPose, MLSD, Scribble, Segmentation, Tile, and Shuffle preprocessors for ControlNet conditioning.