Browse ModelsBriaBria Fibo Video Background Remover

Bria Fibo Video Background Remover

Bria Fibo Video Background Remover

Playground

Try it 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.

Features

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$0.0045

Billing Rules

  • Pricing is $0.0045 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.



<ApiPage model={model}>
  ## Authentication

  For authentication details, please refer to the [Authentication Guide](/docs-authentication).

  ## API Endpoints

  ### Submit Task & Query Result

  ## Parameters

  ### Task Submission Parameters

  #### Request Parameters

  #### Response Parameters

  <SubmitResponse />

  #### Result Request Parameters

  | Parameter | Type | Required | Default | Description |
  |-----------|------|----------|---------|-------------|
  | id | string | Yes | - | Task ID |

  #### Result Response Parameters

  | Parameter | Type | Description |
  |-----------|------|-------------|
  | code | integer | HTTP status code (e.g., 200 for success) |
  | message | string | Status message (e.g., "success") |
  | data | object | The prediction data object containing all details |
  | data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
  | data.model | string | Model ID used for the prediction |
  | data.outputs | string | Array of URLs to the generated content. |
  | data.urls | object | Object containing related API endpoints |
  | data.urls.get | string | URL to retrieve the prediction result |
  | data.status | string | Status of the task: `created`, `processing`, `completed`, or `failed` |
  | data.created_at | string | ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z") |
  | data.error | string | Error message (empty if no error occurred) |
  | data.timings | object | Object containing timing details |
  | data.timings.inference | integer | Inference time in milliseconds |

</ApiPage>

  
© 2025 WaveSpeedAI. All rights reserved.