Serving Quick Start

hypergen serve stabilityai/stable-diffusion-xl-base-1.0

INFO - Starting HyperGen server...
INFO - Model: stabilityai/stable-diffusion-xl-base-1.0
INFO - Device: cuda
INFO - Host: 0.0.0.0
INFO - Port: 8000
INFO - Initializing model worker...
INFO - Server ready!

pip install openai pillow

from openai import OpenAI
import base64
from pathlib import Path

# Create client
client = OpenAI(
    api_key="not-needed",  # No auth by default
    base_url="http://localhost:8000/v1"
)

# Generate images
response = client.images.generate(
    model="sdxl",
    prompt="A cat holding a sign that says hello world",
    n=2,
    size="1024x1024",
    response_format="b64_json"
)

# Save images
for i, img_data in enumerate(response.data):
    img_bytes = base64.b64decode(img_data.b64_json)
    Path(f"output_{i}.png").write_bytes(img_bytes)
    print(f"Saved output_{i}.png")

curl http://localhost:8000/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A serene mountain landscape",
    "n": 1,
    "size": "1024x1024"
  }'

import requests
import base64

response = requests.post(
    "http://localhost:8000/v1/images/generations",
    json={
        "prompt": "A sunset over the ocean",
        "n": 1,
        "size": "1024x1024",
        "response_format": "b64_json",
        "num_inference_steps": 30,
        "guidance_scale": 7.5
    }
)

data = response.json()

# Save first image
img_bytes = base64.b64decode(data["data"][0]["b64_json"])
with open("sunset.png", "wb") as f:
    f.write(img_bytes)

hypergen serve stabilityai/stable-diffusion-xl-base-1.0 \
  --api-key your-secret-key-here

client = OpenAI(
    api_key="your-secret-key-here",
    base_url="http://localhost:8000/v1"
)

hypergen serve stabilityai/stable-diffusion-xl-base-1.0 --port 8080

hypergen serve black-forest-labs/FLUX.1-dev --dtype bfloat16

hypergen serve stabilityai/stable-diffusion-xl-base-1.0 \
  --lora ./my_trained_lora

hypergen serve stabilityai/stable-diffusion-xl-base-1.0

hypergen serve black-forest-labs/FLUX.1-dev \
  --dtype bfloat16 \
  --max-queue-size 50

hypergen serve runwayml/stable-diffusion-v1-5 \
  --port 8000

hypergen serve stabilityai/stable-diffusion-xl-base-1.0 \
  --host 0.0.0.0 \
  --port 8000 \
  --api-key $(openssl rand -hex 32) \
  --dtype float16 \
  --max-queue-size 100 \
  --max-batch-size 4

response = client.images.generate(
    model="sdxl",
    prompt="A beautiful landscape",
    num_inference_steps=30,  # Faster but lower quality
    # Or 50-100 for higher quality
)

response = client.images.generate(
    model="sdxl",
    prompt="A portrait of a person",
    negative_prompt="blurry, low quality, distorted",
)

response = client.images.generate(
    model="sdxl",
    prompt="A cat in a garden",
    seed=42,  # Same seed = same image
)

response = client.images.generate(
    model="sdxl",
    prompt="Abstract art",
    guidance_scale=12.0,  # Higher = stricter prompt following
)

response = client.images.generate(
    model="sdxl",
    prompt="A robot playing guitar",
    n=4,  # Generate 4 variations
)

for i, img_data in enumerate(response.data):
    # Save each image
    pass

curl http://localhost:8000/health

{
  "status": "healthy",
  "model": "stabilityai/stable-diffusion-xl-base-1.0",
  "queue_size": 0,
  "device": "cuda"
}

curl http://localhost:8000/v1/models

{
  "object": "list",
  "data": [
    {
      "id": "stabilityai/stable-diffusion-xl-base-1.0",
      "object": "model",
      "created": 1234567890,
      "owned_by": "hypergen"
    }
  ]
}

#!/usr/bin/env python3
"""
Generate images using HyperGen server.

Usage:
    python generate.py "A cat holding a sign"
"""

import sys
import base64
from pathlib import Path
from openai import OpenAI

def generate_image(prompt: str, output: str = "output.png"):
    """Generate an image from a prompt."""
    client = OpenAI(
        api_key="not-needed",
        base_url="http://localhost:8000/v1"
    )

    print(f"Generating: {prompt}")

    response = client.images.generate(
        model="sdxl",
        prompt=prompt,
        n=1,
        size="1024x1024",
        response_format="b64_json",
        num_inference_steps=50,
        guidance_scale=7.5
    )

    # Save image
    img_bytes = base64.b64decode(response.data[0].b64_json)
    Path(output).write_bytes(img_bytes)

    print(f"Saved to: {output}")

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python generate.py 'your prompt here'")
        sys.exit(1)

    prompt = sys.argv[1]
    generate_image(prompt)

python generate.py "A serene Japanese garden with cherry blossoms"

# Use a different port
hypergen serve model_id --port 8001