Pruna AI P Video Edit API Documentation

Pruna AI P Video Edit API Documentation

Playground

Pruna P-Video-Edit is an instruction-based video editing model for modifying subjects, objects, attributes, and environments in existing videos, with optional reference-image guidance and Draft or Full quality modes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Pruna AI P-Video Edit edits an existing video using natural-language instructions. Upload a source video, describe the changes you want, and optionally add reference images to guide identity, appearance, style, object edits, or scene transformation.

Why Choose This?

• Instruction-based video editing
  Edit videos with natural-language prompts instead of building a manual editing workflow.

• Flexible visual changes
  Modify attributes, transform objects, adjust environments, or restyle a scene while preserving the source video’s motion and structure.

• Reference-guided editing
  Add up to 4 reference images to guide identity, appearance, object design, or visual style.

• Draft and Full modes
  Use Draft mode for faster, lower-cost previews, or Full mode for higher-quality edits.

• Audio preservation
  Preserve the source video’s audio in the edited result with save_audio.

Parameters

How to Use

1. Upload a source video — Provide a clip no longer than 15 seconds.
2. Write the edit prompt — Describe what should change and what should remain consistent.
3. Add reference images optional — Provide up to 4 images when identity, style, product, or object appearance matters.
4. Choose Draft or Full mode — Use Draft mode for quick previews or Full mode for higher-quality output.
5. Choose audio behavior — Keep save_audio enabled when the source audio should be preserved.
6. Set seed optional — Use a fixed seed when reproducibility is needed.
7. Submit — Generate the edited video and retrieve the output URL.

Pricing

Pricing is based on the source video duration and selected mode.

Billing duration is rounded up to the next whole second, with a minimum billed duration of 1 second and a maximum billed duration of 15 seconds.

Example Costs

images, prompt_upsampling, save_audio, and seed do not add separate charges.

Best Use Cases

• Attribute editing — Change clothing, materials, colors, lighting, or visual traits.
• Object modification — Replace, transform, add, or restyle objects in a scene.
• Environment replacement — Move an existing performance into a different location, season, time of day, or visual atmosphere.
• Reference-guided edits — Use images to guide identity, object appearance, product design, or visual style.
• Creative iteration — Generate Draft previews before producing a Full-quality result.
• Social and marketing video edits — Adapt short clips for ads, product showcases, and creative campaigns.

Pro Tips

• Clearly describe both what should change and what should remain consistent.
• Use reference images when identity, product details, object design, or style consistency matters.
• Use Draft mode for fast iteration before running a Full edit.
• Keep prompts focused on one main edit direction for more stable results.
• Preserve save_audio=true when the original soundtrack, dialogue, or ambience should remain.
• Use short, clean source videos with clear subjects and stable motion.
• Set a fixed seed when comparing prompt or reference-image changes.

Notes

• video and prompt are required.
• The input video can be up to 15 seconds long.
• images is optional and supports up to 4 reference images.
• Defaults: prompt_upsampling=true, draft=false, and save_audio=true.
• The completed prediction returns the edited video as a URL in outputs.
• This endpoint does not expose output resolution, frame rate, duration, output format, or translation controls.

Related Models

• Pruna AI P-Image Ideogram — Generate images with prompt-based visual and typography control.
• Pruna AI P-Video Replace — Replace or transform video elements with prompt and reference guidance.
• Pruna AI P-Image Edit — Edit images with natural-language instructions and reference inputs.

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'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "prompt_upsampling": true,
  "draft": false,
  "save_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-video/edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters