Aquiles-ai/Aquiles-Image

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

44
/ 100
Emerging

Supports intelligent request batching that groups operations by shared parameters for throughput optimization across single or multi-GPU setups, and includes 30+ pre-optimized models spanning text-to-image (FLUX, SD3.5, Qwen), image-to-image editing, and text-to-video generation (Wan2.x, HunyuanVideo with turbo variants). Built on FastAPI with dynamic load balancing for distributed inference, it enables seamless switching from OpenAI's API using their official Python client without code changes.

Available on PyPI.

Maintenance 13 / 25
Adoption 13 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2026

Monthly downloads

792

Commits (30d)

0

Dependencies

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Aquiles-ai/Aquiles-Image"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.