Flux V1 Pro Erase API Documentation

Flux V1 Pro Erase API Documentation

Playground

Try it on WaveSpeedAI!

FLUX.1 Pro Erase is a fast AI object removal and image inpainting model that removes objects from images using a black-and-white mask, then fills the selected area with natural, context-aware detail. Ready-to-use REST inference API for object removal, photo cleanup, product image editing, background repair, creative retouching, marketing assets, and professional image editing workflows with simple integration, no coldstarts, and affordable pricing.

Features

WaveSpeed AI FLUX V1 Pro Erase removes selected elements from an image using a mask, then fills the masked region with regenerated content that blends naturally with the surrounding scene. It is suitable for object removal, cleanup, retouching, and image refinement workflows.


Why Choose This?

  • Mask-based object removal Remove unwanted objects, distractions, or visual clutter from an image with a dedicated mask input.

  • Clean scene-aware fill Regenerate the selected region so it blends with the surrounding image content.

  • Simple erase workflow Upload an image, provide a mask, and generate a cleaned result.

  • Multiple output formats Export the result in supported formats such as jpeg.

  • Production-ready API Suitable for photo cleanup, product image refinement, background editing, and visual post-processing workflows.


Parameters

ParameterRequiredDescription
imageYesInput image to edit.
mask_imageYesMask image indicating the region to erase and regenerate.
output_formatNoOutput image format, such as jpeg.

How to Use

  1. Upload your image — provide the source image you want to clean up.
  2. Upload the mask — mark the object or region you want to erase.
  3. Choose output format (optional) — select the format that best fits your workflow.
  4. Submit — run the model and download the cleaned image.

Example Use Case

Remove small desk objects from a workspace photo so the final scene looks cleaner and more minimal.


Pricing

Just $0.08 per image.

Billing Rules

  • Each erase request costs $0.08
  • Pricing is fixed per image

Best Use Cases

  • Object removal — Remove unwanted items, clutter, or distractions from photos.
  • Photo cleanup — Refine scenes for cleaner presentations and commercial use.
  • Product image retouching — Remove background props or accidental objects from listings and ads.
  • Creative editing — Clear space in an image before adding other edits or design elements.
  • Workflow preparation — Clean up images before downstream compositing or publishing.

Pro Tips

  • Use a precise mask for better removal quality.
  • Avoid masking too much of the image at once unless the surrounding context is strong.
  • Use the cleanest source image possible for more natural regeneration.
  • Export as jpeg for convenience, or choose another format when your workflow needs it.

Notes

  • Both image and mask_image are required.
  • Pricing is fixed at $0.08 per image.
  • Better masks generally produce cleaner erase results.

  • WaveSpeed AI image editing workflows — Useful when you need broader prompt-based transformations instead of object removal only.
  • WaveSpeed AI inpainting workflows — Useful when you want more general masked-region regeneration tasks.
  • WaveSpeed AI text-to-image workflows — Useful when you need fresh image generation rather than editing an existing image.

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",
  "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "output_format": "jpeg"
}
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/wavespeed-ai/flux-v1-pro/erase" \
  -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

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The input image to erase content from.
mask_imagestringYes-Black/white mask image. White pixels mark the region to erase, black pixels mark the region to keep. The mask must match the input image dimensions.
output_formatstringNojpegjpeg, pngThe format of the generated image.

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

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.