This repository contains an implementation of the FLUX.1 [schnell]
FP8 version, which utilizes float8 numerics instead of bfloat16. This update allows for a 2x performance improvement, significantly speeding up inference tasks when deployed via Fireworks AI’s Flumina Server App toolkit.
This FP8 Server App is deployed to Fireworks as-is in a "serverless" deployment, offering high-speed, hassle-free performance.
Grab an
API Key from Fireworks and set it in your environment variables:
1curl -X POST 'https://api.fireworks.ai/inference/v1/workflows/accounts/fireworks/models/flux-1-schnell-fp8/text_to_image' \
2 -H "Authorization: Bearer $API_KEY" \
3 -H "Content-Type: application/json" \
4 -H "Accept: image/jpeg" \
5 -d '{
6 "prompt": "Woman laying in the grass",
7 "aspect_ratio": "16:9",
8 "guidance_scale": 3.5,
9 "num_inference_steps": 4,
10 "seed": 0
11 }' \
12 --output output.jpg
Flumina is Fireworks.ai’s innovative platform for hosting Server Apps that lets users deploy deep learning inference to production environments in just minutes.
