Pruna AI P Image Edit API Documentation

Pruna AI P Image Edit API Documentation

Playground

Pruna AI P-Image Edit is a fast AI image editing model that edits and transforms images based on text instructions and reference images. Ready-to-use REST inference API for photo retouching, creative edits, product image updates, background changes, marketing assets, and AI image editing workflows with simple integration, no coldstarts, and affordable pricing.

Features

Pruna AI P-Image Edit transforms one or more reference images using natural-language editing instructions. It is designed for image modification workflows such as outfit changes, style transfer, object replacement, visual refinement, and other prompt-guided image edits.

Why Choose This?

• Prompt-driven image editing Edit images by describing exactly what you want to change in natural language.

• Multi-image reference support Upload one or more images to guide the edit, making it easier to preserve identity, style, or visual consistency.

• Flexible aspect ratio control Choose the output aspect ratio that best fits your use case.

• Multiple output formats Export the edited image in a supported format such as png.

• Seed support for reproducibility Use seed to get more consistent results across repeated edits.

• Simple fixed pricing Each edit run uses a straightforward per-image price.

Parameters

How to Use

1. Upload your reference images — provide one or more images you want to use for the edit.
2. Write your prompt — describe what should change and what should stay consistent.
3. Choose aspect ratio (optional) — leave empty to match the first input image, or select an output ratio.
4. Choose output format (optional) — select the format that best fits your workflow.
5. Set a seed (optional) — use a fixed seed for more reproducible results.
6. Submit — run the model and download the edited image.

Example Prompt

Change the figure 1 man’s suit to the clothes in figure 2.

Pricing

Just $0.01 per image.

Best Use Cases

• Outfit and apparel changes — Replace clothing or accessories while preserving the subject.
• Style transfer — Apply the look or styling of one image to another.
• Visual refinement — Improve or adjust details using prompt-based instructions.
• Character consistency edits — Modify appearance while keeping identity and composition stable.
• Creative image adaptation — Rework an existing image into a new variation for marketing, design, or social content.
• Reference-guided editing — Use multiple images when you need stronger control over the desired result.

Pro Tips

• Be specific about what should change and what should remain unchanged.
• If using multiple images, make sure each image clearly supports the edit you want.
• Mention identity, clothing, background, or composition explicitly when consistency matters.
• Use the same seed when you want to iterate on an edit with more consistent outputs.
• Keep prompts short and direct for simple edits, and add more detail only when necessary.

Notes

• Both prompt and images are required.
• images can include one or more reference images.
• seed helps with reproducibility but may not guarantee identical results in every case.
• Pricing is fixed at $0.01 per image.

Related Models

• Pruna AI P-Image Text-to-Image — Generate new images directly from natural-language prompts.
• Other Pruna AI image generation and image editing models may be useful when you need different quality, speed, or workflow trade-offs.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "1:1",
  "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/edit" \
  -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