SB

Available through Replicate — FLUX

sdxl

sdxl on replicate · Replicate

What it takes and gives

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

Best fordeclared, not tested

Stylised and non-photoreal work where a negative prompt does the steering.

Good at

takes a negative promptwide LoRA/community ecosystempixel-artstylised

Not for

weaker prompt adherence than Flux

Licence

CreativeML Open RAIL++-M · Commercial use: yes

Made by Stability AI

Every model's licence

What comes out

Production quality — 1024px typical on the shorter side, across 9 images

Speed and reliability

Replicate: 2 runs in 30 days · 100% completed

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 sdxl (returns workflowId)
curl -X POST "https://app.sushibelt.ai/api/v1/workflows" \
  -H "Authorization: Bearer $SUSHIBELT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name":"sdxl","projectId":"'"$PROJECT_ID"'","steps":[{"key":"subject","type":"TextEntry","config":{"text":"a red fox in the snow","apiInputKey":"prompt"}},{"key":"image","type":"DiffusionWorker","config":{"providerKey":"replicate","model":"sdxl"},"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 Replicate account. Through the API it runs only on your own Replicate key.

Runs on your own Replicate key, or on credits

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

How it’s used →

Made with this

text-to-imageimage-to-image

In 2 templates · 9 published outputs

Workflows