SB
Sign inRequest an invite

Available through FAL — FLUX

flux-schnell

flux-schnell on fal_ai · Fal.ai

What it takes and gives

a prompt → an image · seed, strength, steps, guidance, aspect ratio, variations

Best fordeclared, not tested

Fast iteration while you are still deciding what you want.

Good at

4-step, cheap enough to try ten variationspainterlystylised

Not for

less detail than flux-devno negative prompt

Licence

Apache 2.0 · Commercial use: yes

Made by Black Forest Labs

Every model's licence

Price

About 0.39 credits per image · measured on real runs

Speed and reliability

4 runs in 30 days · typically 2.8 s · Fal.ai: 9 runs in 30 days

Also runs on

Run it from code

With a team API key and a project id. The run answers with a jobId; poll GET /api/v1/runs/{jobId} for the image.

# 1. Once: a workflow that runs flux-schnell (returns workflowId)
curl -X POST "https://app.sushibelt.ai/api/v1/workflows" \
  -H "Authorization: Bearer $SUSHIBELT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name":"flux-schnell","projectId":"'"$PROJECT_ID"'","steps":[{"key":"subject","type":"TextEntry","config":{"text":"a red fox in the snow","apiInputKey":"prompt"}},{"key":"image","type":"DiffusionWorker","config":{"providerKey":"fal_ai","model":"flux-schnell"},"inputs":["subject"]}]}'

# 2. Run it, with your own prompt
curl -X POST "https://app.sushibelt.ai/api/v1/workflows/$WORKFLOW_ID/runs" \
  -H "Authorization: Bearer $SUSHIBELT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"inputs":{"prompt":"a red fox in the snow"}}'

Where it runs

In app · own key on APIRuns in the app on Sushibelt's Fal.ai account. Through the API it runs only on your own Fal.ai key.

Runs on your own Fal.ai key, or on credits

On your own key, Fal.ai’s terms apply to your team directly.

What we learned

Consistently the faster of the two places this model runs — about 1.4 s quicker than Replicate, at twice the price. Worth it for anything a person is sitting in front of.

How it’s used →

Made with this

CONCEPT
text-to-imageimage-to-image

In 3 templates · 1 published output

Workflows

Next step3D objects Images
Start building