aquiles-image 0.2.8

A high-performance, memory-efficient inference server for diffusion models, compatible with the OpenAI client

Aquiles-Image

Self-hosted image generation with OpenAI-compatible APIs

🚀 FastAPI • Diffusers • Drop-in replacement for OpenAI

🎯 What is Aquiles-Image?

Aquiles-Image is a production-ready API server that lets you run state-of-the-art image generation models on your own infrastructure. OpenAI-compatible by design, you can switch from external services to self-hosted in under 5 minutes.

Why Aquiles-Image?

Challenge	Aquiles-Image Solution
💸 Expensive external APIs	Run models locally with unlimited usage
🔒 Data privacy concerns	Your images never leave your server
🐌 Slow inference	Advanced optimizations for 3x faster generation
🔧 Complex setup	One command to run any supported model
🚫 Vendor lock-in	OpenAI-compatible, switch without rewriting code

Key Features

• 🔌 OpenAI Compatible - Use the official OpenAI client with zero code changes
• ⚡ 3x Faster - Advanced inference optimizations out of the box
• 🎨 10+ Models - FLUX.1, FLUX.2, SD3.5, and more preconfigured
• 🛠️ Superior DevX - Simple CLI, dev mode for testing, built-in monitoring
• 🎬 Experimental Video - Text-to-video generation support (Wan2.2)

🚀 Quick Start

Installation

# From PyPI (recommended)
pip install aquiles-image

# From source
git clone https://github.com/Aquiles-ai/Aquiles-Image.git
cd Aquiles-Image
pip install .

Launch Server

aquiles-image serve --model "stabilityai/stable-diffusion-3.5-medium"

Generate Your First Image

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:5500", api_key="not-needed")

result = client.images.generate(
    model="stabilityai/stable-diffusion-3.5-medium",
    prompt="a white siamese cat",
    size="1024x1024"
)

print(f"Image URL: {result.data[0].url}")

That's it! You're now generating images with the same API you'd use for OpenAI.

🎨 Supported Models

Text-to-Image (/images/generations)

• stabilityai/stable-diffusion-3-medium
• stabilityai/stable-diffusion-3.5-medium
• stabilityai/stable-diffusion-3.5-large
• stabilityai/stable-diffusion-3.5-large-turbo
• black-forest-labs/FLUX.1-dev
• black-forest-labs/FLUX.1-schnell
• black-forest-labs/FLUX.1-Krea-dev
• black-forest-labs/FLUX.2-dev
• diffusers/FLUX.2-dev-bnb-4bit
• Tongyi-MAI/Z-Image-Turbo

Image-to-Image (/images/edits)

• black-forest-labs/FLUX.1-Kontext-dev
• diffusers/FLUX.2-dev-bnb-4bit

Text-to-Video (/videos) - Experimental

• Wan-AI/Wan2.2-T2V-A14B (High quality, 40 steps - requires H100/A100-80G, start with --model "wan2.2")
• Aquiles-ai/Wan2.2-Turbo ⚡ 9.5x faster - Same quality in 4 steps! (requires H100/A100-80G, start with --model "wan2.2-turbo")

VRAM Requirements: Most models need 24GB+ VRAM. Video generation requires 80GB+ (H100/A100-80G).

📖 Full models documentation and more models in 🎬 Aquiles-Studio

💡 Examples

Generating Images

https://github.com/user-attachments/assets/00e18988-0472-4171-8716-dc81b53dcafa

https://github.com/user-attachments/assets/00d4235c-e49c-435e-a71a-72c36040a8d7

Editing Images

Input + Prompt	Result

Generating Videos (Experimental)

https://github.com/user-attachments/assets/7b1270c3-b77b-48df-a0fe-ac39b2320143

Note: Video generation with wan2.2 takes ~30 minutes on H100. With wan2.2-turbo, it takes only ~3 minutes! Only one video can be generated at a time.

🧪 Advanced Features

AutoPipeline - Run Any Diffusers Model

Run any model compatible with AutoPipelineForText2Image from HuggingFace:

aquiles-image serve \
  --model "stabilityai/stable-diffusion-xl-base-1.0" \
  --auto-pipeline \
  --set-steps 30

Supported models include:

• stable-diffusion-v1-5/stable-diffusion-v1-5
• stabilityai/stable-diffusion-xl-base-1.0
• Any HuggingFace model compatible with AutoPipelineForText2Image

Trade-offs:

• ⚠️ Slower inference than native implementations
• ⚠️ No LoRA or adapter support
• ⚠️ Experimental - may have stability issues

Dev Mode - Test Without Loading Models

Perfect for development, testing, and CI/CD:

aquiles-image serve --no-load-model

What it does:

• Starts server instantly without GPU
• Returns test images that simulate real responses
• All endpoints functional with realistic formats
• Same API structure as production

🎯 Use Cases

Who	What
🚀 AI Startups	Build image generation features without API costs
👨‍💻 Developers	Prototype with multiple models using one interface
🏢 Enterprises	Scalable, private image AI infrastructure
🔬 Researchers	Experiment with cutting-edge models easily

📋 Prerequisites

• Python 3.8+
• CUDA-compatible GPU with 24GB+ VRAM (most models)
• 10GB+ free disk space

📚 Documentation

• Full Documentation
• Client Reference
• Model Guide

⭐ Star this project • 🐛 Report issues

Built with ❤️ for the AI community