Stable Diffusion Einrichtung: Self-Hosted Bilderzeugung

# Abhängigkeiten
sudo apt-get update
sudo apt-get install -y python3-venv python3-pip git wget

# Repository klonen
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
cd stable-diffusion-webui

# Modell herunterladen (Stable Diffusion XL)
wget -O models/Stable-diffusion/sd_xl_base_1.0.safetensors \
  "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors"

# Starten
./webui.sh --listen --port 7860 --xformers --enable-insecure-extension-access

version: '3.8'
services:
  stable-diffusion:
    image: ghcr.io/abetlen/stable-diffusion-webui-docker:latest
    container_name: sd-webui
    ports:
      - "7860:7860"
    volumes:
      - sd_models:/app/models
      - sd_outputs:/app/outputs
      - sd_extensions:/app/extensions
    environment:
      - COMMANDLINE_ARGS=--listen --xformers --enable-insecure-extension-access --no-half-vae
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped

volumes:
  sd_models:
  sd_outputs:
  sd_extensions:

# Repository klonen
git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI

# Python virtuelle Umgebung
python3 -m venv venv
source venv/bin/activate

# Abhängigkeiten
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txt

# Starten
python main.py --listen 0.0.0.0 --port 8188

# Stable Diffusion XL Base
wget -O models/Stable-diffusion/sd_xl_base_1.0.safetensors \
  "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors"

# Stable Diffusion 1.5 (für niedrigen VRAM)
wget -O models/Stable-diffusion/v1-5-pruned-emaonly.safetensors \
  "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"

# LoRA-Modelle im Verzeichnis models/Lora ablegen
mkdir -p models/Lora

a beautiful landscape, mountains, sunset <lora:detail-enhancer:0.7>

# ControlNet-Erweiterung installieren (AUTOMATIC1111)
cd extensions
git clone https://github.com/Mikubill/sd-webui-controlnet.git

# ControlNet-Modelle
mkdir -p models/ControlNet
wget -O models/ControlNet/control_v11p_sd15_canny.pth \
  "https://huggingface.co/lllyasviel/ControlNet-v1-1/resolve/main/control_v11p_sd15_canny.pth"

import requests
import base64
from pathlib import Path

def generate_image(prompt, negative_prompt="", steps=30, width=1024, height=1024):
    url = "http://localhost:7860/sdapi/v1/txt2img"
    payload = {
        "prompt": prompt,
        "negative_prompt": negative_prompt,
        "steps": steps,
        "width": width,
        "height": height,
        "sampler_name": "DPM++ 2M Karras",
        "cfg_scale": 7,
        "seed": -1
    }
    
    response = requests.post(url, json=payload)
    result = response.json()
    
    image_data = base64.b64decode(result["images"][0])
    Path("output.png").write_bytes(image_data)
    print("Bild gespeichert: output.png")

generate_image(
    prompt="a futuristic data center, neon lights, cyberpunk style, 8k",
    negative_prompt="blurry, low quality, distorted"
)

# Speicheroptimierung mit xformers
pip install xformers

# Startparameter
./webui.sh --listen --xformers --opt-sdp-attention --no-half-vae --medvram --port 7860