Pruna AI P Image Upscale API Documentation

Pruna AI P Image Upscale API Documentation

Playground

Pruna AI P-Image Upscale is a fast AI image upscaling model that enhances image resolution and improves visual detail. Ready-to-use REST inference API for product photos, portraits, design assets, e-commerce images, social media visuals, and image enhancement workflows with simple integration, no coldstarts, and affordable pricing.

Features

Pruna AI P-Image Upscale enhances and enlarges images with a simple workflow built around target size selection and flexible output formatting. It is suitable for restoring old images, improving low-resolution assets, preparing sharper visuals for design or marketing, and generating cleaner outputs for downstream use.

Why Choose This?

• Simple image upscaling Upload a single image and generate a higher-quality result with minimal configuration.

• Target-based output control Use the target setting to choose the desired upscale level or output target.

• Clean enhancement workflow Improve image clarity for photos, scans, product images, and other visual assets.

• Flexible output format Export the upscaled image in a supported format such as png.

• Affordable tiered pricing Uses a simple pricing structure based on the selected target tier.

Parameters

How to Use

1. Upload your image — provide the source image you want to enhance.
2. Choose the target — select the upscale target that best matches your quality needs.
3. Choose output format (optional) — select the format that best fits your workflow.
4. Submit — run the model and download the upscaled image.

Example Use Case

Upscale an old street photograph to produce a cleaner, sharper version for archival, presentation, or creative reuse.

Pricing

Pricing is based on the selected target tier.

Billing Rules

• Requests with target <= 4 cost $0.005 per image
• Requests with target > 4 and <= 8 cost $0.010 per image
• Requests with target > 8 and <= 16 cost $0.020 per image
• Requests with target > 16 and <= 32 cost $0.040 per image
• Requests with target > 32 and <= 64 cost $0.060 per image
• Requests with target > 64 and <= 128 cost $0.120 per image
• Pricing depends on the selected target
• output_format does not affect pricing

Best Use Cases

• Old photo enhancement — Improve the clarity of scanned or low-resolution photographs.
• Design asset preparation — Create sharper source images for layouts, presentations, and creative projects.
• Product image improvement — Upscale commercial visuals for catalogs, ads, and marketplace listings.
• Archival restoration workflows — Produce cleaner and larger outputs from legacy image assets.
• General low-resolution cleanup — Improve images that need a simple boost in size and quality.

Pro Tips

• Start with a lower target setting first if you want a faster and cheaper test run.
• Use a clean source image whenever possible for better enhancement results.
• Choose a higher target only when you actually need the larger or stronger upscale output.
• png is a good choice when you want to preserve output quality.

Notes

• image is the only required field.
• target now supports values up to 128.
• Pricing depends on the selected target tier.
• output_format changes the file type, but not the price.
• Higher target values may be more suitable for print, detailed review, or premium delivery workflows.

Related Models

• Pruna AI P-Image Text-to-Image — Generate new images directly from text prompts.
• Pruna AI P-Image Edit — Edit existing images with natural-language instructions.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "target": 4,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-image/upscale" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters