Z-Image Turbo Img2Img

Run it

The smallest request that works: the required fields only.

curl https://api.percify.io/v3/playground/v1/run \
  -H "Authorization: Bearer $PERCIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "z-image-turbo-img2img",
    "input": {
      "prompt": "A young Asian woman with long, vibrant purple hair stands on a sunlit sandy beach, posi...",
      "image": "https://example.com/input.png"
    }
  }'

1. EstimatePOST /estimate with the same body returns the price and charges nothing.
2. RunPOST /run returns an id at once, with status processing.
3. CollectGET /generations/{id}?wait=55 returns the file URLs, or pass a webhook.

Parameters

10 fields in input, required first.

• promptRequired
  string

  Text prompt for image generation

• imageRequired
  URL

  Input image for img2img

• strengthOptional
  numberDefault 0.6

  Strength of the img2img transformation. 0.0 is no change, 1.0 is full transformation

• num_inference_stepsOptional
  integerDefault 8

  Number of inference steps. This actually results in (num_inference_steps - 1) DiT forwards

• guidance_scaleOptional
  numberDefault 0

  Guidance scale. Should be 0 for Turbo models

• seedOptional
  integer

  Random seed. Set for reproducible generation

• lora_weightsOptional
  array

  LoRA weights as an array of URLs. Supports.safetensors URLs, tar files, and zip files (e.g., ['https://example.com/lora1.safetensors', 'https://example.com/lora2.safetensors'])

• lora_scalesOptional
  array

  Scales for each LoRA as an array of floats. Must match the number of lora_weights. Defaults to 1.0 for each if not provided.

• output_formatOptional
  png, jpg, webpDefault jpg

  Format of the output images

• output_qualityOptional
  integerDefault 80

  Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for.png outputs