Black Forest Labs Flux 3 Video Upscale API Documentation

Black Forest Labs Flux 3 Video Upscale API Documentation

Playground

FLUX Video Upscale enhances MP4 videos with source-faithful or creative detail reconstruction, configurable 1.5x to 3x scaling, and improved visual clarity for video restoration, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX 3 Video Upscale enhances an input video with AI-powered upscaling. Upload a source video, optionally describe the desired enhancement direction with a prompt, choose an upscale factor, and adjust creativity to control how much visual detail the model reconstructs during the upscale process.

Why Choose This?

• AI video upscaling
  Improve video resolution and perceived detail from an existing source clip.

• Prompt-guided enhancement
  Use an optional prompt to guide the visual direction, such as sharper details, cleaner textures, or more cinematic refinement.

• Adjustable upscale factor
  Control how strongly the output should be upscaled with the upscale_factor parameter.

• Creativity control
  Use creativity to control the enhancement strength and reconstruction behavior.

• Short video enhancement workflow
  Designed for upgrading short video clips while preserving the original motion and scene structure.

• Simple input pipeline
  Provide a video, set the upscale parameters, and generate an enhanced output.

Parameters

How to Use

1. Upload the input video — Provide the source video you want to upscale.
2. Add a prompt optional — Describe the desired enhancement style, such as sharper detail, cleaner lighting, reduced softness, or cinematic refinement.
3. Set upscale factor — Choose how strongly the video should be upscaled.
4. Adjust creativity — Use creativity to control the amount of visual reconstruction.
5. Submit — Generate the upscaled video and retrieve the output.

Pricing

Pricing is based on input video duration and the selected creativity value. The highest (4K) pricing tier applies to every request, regardless of output resolution or upscale_factor.

Billable duration is rounded up to the next whole second, with a minimum of 1 second and a maximum of 20 seconds. The default creativity value is 1 (creative).

For example, a 10-second video costs $7.90 in creative mode or $5.50 in precise mode.

Best Use Cases

• Video enhancement — Improve short video clips with AI upscaling.
• Creative restoration — Add sharper detail and cleaner visual structure to soft or lower-resolution footage.
• Marketing assets — Upgrade short product, campaign, or social media clips.
• Preview-to-final workflows — Improve draft videos before publishing or presenting.
• Cinematic refinement — Enhance lighting, texture, and perceived detail while preserving the source motion.
• Social video optimization — Upscale short clips for higher-quality platform delivery.

Pro Tips

• Use clean source videos with stable motion for better upscaling results.
• Add a prompt when you want a specific enhancement direction, such as sharper product details, cleaner faces, or more cinematic lighting.
• Keep prompts focused on enhancement rather than changing the scene content.
• Use creativity carefully when the original video needs stronger detail reconstruction.
• Short clips are easier to review and iterate before processing longer videos.
• Make sure the source video already has the motion and composition you want, since this endpoint is designed for upscaling rather than video editing.

Related Models

• FLUX 3 Text-to-Video — Generate video directly from a text prompt.
• FLUX 3 Image-to-Video — Animate a reference image into a video.
• FLUX 3 Start-End-to-Video — Generate a video between a start image and an end image.
• FLUX 3 Video Extend — Extend an existing video with a new generated continuation.

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",
  "upscale_factor": 2,
  "creativity": 1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/video-upscale" \
  -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