Seedream 5.0 Pro yayında | Görsel Üretici'de deneyin →
Ana Sayfa/Keşfet/Bria/Fibo/Video Background Remover

Fibo Video Background Remover

bria /

Bria Video Background Remover removes the background from videos with support for transparency and custom background colors. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

ai-remover
Giriş

Boşta

$0.05çalıştırma başına·~20 / $1

ÖrneklerTümünü görüntüle

İlgili Modeller

README

Bria Fibo Video Background Remover

Bria Fibo Video Background Remover is an AI-powered video processing model that removes backgrounds from videos with strong temporal consistency and clean subject separation. Upload your video, choose a replacement background color, and generate a processed result suitable for compositing, social content, product videos, and professional editing workflows.

What's New in V-RMBG 3.0

Bria’s V-RMBG 3.0 is now live as a major upgrade to Bria’s production-ready video background removal stack.

  • State-of-the-art upgrade — Built as an end-to-end video background removal workflow for production use.
  • Stronger benchmark performance — Reported 63%+ success rate against major competitors.
  • Faster processing — Up to 9× faster than earlier approaches.
  • Autoregressive temporal modeling — Each frame conditions on the previous frame’s mask for improved consistency.
  • Cleaner edges across the full clip — Better stability, reduced flicker, and more reliable subject boundaries over time.

Why Choose This?

  • Clean background removal
    Precisely separates subjects from backgrounds across all video frames.

  • Multiple background colors
    Replace the background with transparent output or solid colors such as black, white, gray, red, green, blue, yellow, cyan, or magenta.

  • Temporal consistency
    Maintains smoother, more stable output throughout the full video.

  • Audio preservation
    Optionally keep the original audio track in the output.

  • Flexible output formats
    Export as WebM VP9 or other supported container/codec combinations depending on your workflow.

  • Production-ready workflow
    Useful for compositing, creator content, product isolation, and professional post-production.

Parameters

ParameterRequiredDescription
videoYesSource video for background removal (URL or upload).
background_colorNoReplacement color: Transparent, Black, White, Gray, Red, Green, Blue, Yellow, Cyan, Magenta.
output_container_and_codecNoOutput format option. Default: webm_vp9.
preserve_audioNoKeep the original audio in the output video. Default: enabled.

Output Format Options

OptionContainerCodecAlpha Support
webm_vp9WebMVP9Yes
mp4_h264MP4H.264No
mp4_h265MP4H.265 / HEVCNo
mov_h265MOVH.265 / HEVCPartial
mov_proresksMOVProRes 4444Yes
mkv_h264MKVH.264No
mkv_h265MKVH.265 / HEVCNo
mkv_vp9MKVVP9Yes
gifGIFYes

Important: If you select Transparent as background_color, you must use an output format that supports alpha, such as webm_vp9, mov_proresks, mkv_vp9, or gif. Otherwise, the request may return a 422 error.

How to Use

  1. Upload your video — provide the source clip you want to process.
  2. Choose a background color — select transparent output or a solid replacement color.
  3. Choose the output format — select the container/codec option that best fits your workflow.
  4. Set audio preference — keep preserve_audio enabled if you want the original audio retained.
  5. Submit — run the model and download the processed video.

Example Use Case

Remove the background from a presenter clip, keep the original audio, and export with transparency for use in a video editor or motion graphics workflow.

Pricing

Billing UnitCost
Per second$0.05

Billing Rules

  • Pricing is $0.05 per second
  • Pricing scales linearly with video duration
  • Output format and background color do not change pricing directly

Best Use Cases

  • Green screen replacement — Remove backgrounds for compositing in video editors.
  • Social media content — Create clean, distraction-free videos.
  • Product videos — Isolate products on simple or transparent backgrounds.
  • Presentations — Extract people or objects for overlays and visual presentations.
  • Content creation — Prepare footage for downstream editing, effects, and post-production.

Pro Tips

  • For transparent-background compositing, use webm_vp9, mov_proresks, mkv_vp9, or gif.
  • Use gif only for short clips where lightweight transparent output matters more than fidelity.
  • mp4_h264 offers strong compatibility, but it does not support transparency.
  • mov_proresks is a strong choice for higher-quality professional editing workflows.
  • Keep preserve_audio enabled when voice, music, or sound effects need to remain intact.
  • Higher subject-background contrast usually improves removal quality.

Notes

  • video is the only required input.
  • Transparent output requires an alpha-supported format.
  • Using Transparent with a non-alpha format may result in an API error.
  • V-RMBG 3.0 improves speed and temporal stability, especially on longer clips and harder edge cases.

Related Models

Not:Bu web sitesi, üçüncü taraflarca sağlanan yapay zeka modellerini kullanmaktadır.

Fibo Video Background Remover API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bria/fibo/video-background-remover with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Fibo Video Background Remover below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "background_color": "Transparent",
    "output_container_and_codec": "webm_vp9",
    "preserve_audio": true
}
JSON
)

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

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

# 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bria/fibo/video-background-remover";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "background_color": "Transparent",
        "output_container_and_codec": "webm_vp9",
        "preserve_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "background_color": "Transparent",
    "output_container_and_codec": "webm_vp9",
    "preserve_audio": True
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bria/fibo/video-background-remover", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Fibo Video Background Remover API — Frequently asked questions

What is the Fibo Video Background Remover API?

Fibo Video Background Remover is a Bria model for object / watermark removal, exposed as a REST API on WaveSpeedAI. Bria Video Background Remover removes the background from videos with support for transparency and custom background colors. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Fibo Video Background Remover API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bria/bria-fibo-video-background-remover.

How much does Fibo Video Background Remover cost per run?

Fibo Video Background Remover starts at $0.050 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Fibo Video Background Remover accept?

Key inputs: `video`, `background_color`, `output_container_and_codec`, `preserve_audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bria/bria-fibo-video-background-remover.

How long does Fibo Video Background Remover take to generate?

Median end-to-end generation time on WaveSpeedAI is around 38 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Fibo Video Background Remover outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Bria). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Fibo Video Background Remover | AI Background & Object Remover API | WaveSpeedAI