ReplicateText to imageComing soon

krea/krea-2-medium

krea/krea-2-medium is a text to image tool from Replicate that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs
In the background
Returns
image
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
prompt requiredtext—Text prompt describing the image.
seednumber (whole)nullRandom seed. Set for reproducible generation.
creativityJSONmediumHow far the model expands on your prompt. 'raw' renders only what you describe; 'low' fills in obvious gaps; 'medium' adds reasonable interpretation; 'high' takes meaningful creative liberty.
aspect_ratioJSON1:1Aspect ratio of the generated image.
moodboard_idtextnullOptional Krea moodboard UUID. Moodboards must first be created in the Krea webapp (https://www.krea.ai/moodboards). Get the UUID from the moodboard share URL: `?share=<uuid>`.
moodboard_strengthnumber
0 to 1
0.35How strongly the moodboard shapes the output.
style_reference_imageslist[]Up to 10 reference images whose style should be transferred to the output. Their style is extracted and applied with the strength controlled by `style_reference_strength`.
style_reference_strengthnumber
0 to 1
0.5How strongly to apply the style of the reference images. 0 means no influence, 1 means the style dominates. Applied to all style reference images.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "krea/krea-2-medium",
    "input": {
      "prompt": "<prompt>"
    }
  }'