ReplicateImage to imageComing soon

qwen/qwen-image-2512

qwen/qwen-image-2512 is an image 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.

Priced by usage

Pricing

$0.026 per image.

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 for image generation.
seednumber (whole)—Random seed. Set for reproducible generation.
imageURL or file—Input image for image2image generation. The aspect ratio of your output will match this image.
widthnumber (whole)
256 to 2048
—Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
heightnumber (whole)
256 to 2048
—Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
go_fasttrue or falsetrueUse the model with additional optimizations for faster generation.
guidancenumber
0 to 10
4Guidance for generated image. Use higher values for stronger prompt adherence.
strengthnumber
0 to 1
0.8Strength for image2image generation. 1.0 corresponds to full destruction of information in image.
aspect_ratioJSON16:9Aspect ratio for the generated image.
output_formatJSONwebpFormat of the output images.
output_qualitynumber (whole)
0 to 100
95Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
negative_prompttext Negative prompt for image generation.
num_inference_stepsnumber (whole)
20 to 50
40Number of denoising steps. Use less steps for faster generation.

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": "qwen/qwen-image-2512",
    "input": {
      "prompt": "<prompt>"
    }
  }'