Running Stable Diffusion Locally
Overview Stable Diffusion is the leading open-source image generation model. Run it locally for unlimited generations with full control over models and settings. Option 1: Automatic1111 WebUI The most popular interface with extensive features. # Clone repository git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui cd stable-diffusion-webui # Run (auto-installs dependencies) ./webui.sh # Linux/Mac webui-user.bat # Windows Access at http://localhost:7860 Option 2: ComfyUI Node-based interface for advanced workflows. git clone https://github.com/comfyanonymous/ComfyUI cd ComfyUI pip install -r requirements.txt python main.py Option 3: Python with Diffusers from diffusers import StableDiffusionPipeline import torch pipe = StableDiffusionPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16 ).to("cuda") image = pipe( prompt="A serene mountain landscape at sunset, photorealistic", negative_prompt="blurry, low quality", num_inference_steps=30, guidance_scale=7.5 ).images[0] image.save("output.png") Popular Models Model Size Best For SDXL 1.0 6.5 GB High quality, general SD 1.5 4 GB Fast, many fine-tunes Juggernaut XL 6.5 GB Photorealistic DreamShaper 4 GB Artistic styles Hardware Requirements Model Min VRAM Recommended SD 1.5 4 GB 8 GB SDXL 8 GB 12 GB SDXL + LoRA 10 GB 16 GB Tips for Better Results Negative prompts: Always use them CFG scale: 7-9 for most cases Steps: 20-30 is usually enough Seed: Fix seed for reproducibility LoRAs: Add style/character consistency Key Resources Automatic1111 ComfyUI CivitAI Models