Bria Video Eraser is an AI video inpainting model that removes unwanted objects, people, logos, and text from footage using natural-language prompts. It tracks targets across frames and reconstructs clean, temporally consistent backgrounds for edit-ready results. Ready-to-use REST API, best performance, no cold starts, affordable pricing.
Idle
$0.07per run·~14 / $1
ExamplesView all
cup
Related Models
README
Bria Video Eraser (Prompt-Based)
Bria Video Eraser is a prompt-driven video editing model that removes unwanted objects from videos using simple text instructions. Describe what to erase (people, objects, or specific elements), and the model performs clean removal with context-aware background reconstruction—ideal for fast cleanup without frame-by-frame work.
Why it stands out
- Prompt-based object removal with minimal setup (just video + prompt).
- Clean inpainting to reconstruct the background and preserve scene continuity.
- copy_audio toggle to keep or remove the original audio in the output.
- Transparent, duration-based pricing with a clear minimum charge and 10-minute cap.
Capabilities
- Prompt-based object detection and removal across frames
- Background reconstruction (inpainting) after removal
- Short-form and long-form clip support (billed up to 600s)
- Optional original audio preservation via copy_audio
Parameters
| Parameter | Description |
|---|---|
| prompt* | Text description of what to remove (e.g., “cup”, “person on the right”, “red backpack”). Keep it short and specific. |
| video* | Input video file or public URL. |
| copy_audio | Whether to keep the original audio in the output video (true = preserve, false = remove). |
How to use
- Upload the video (or paste a public URL).
- Write a clear prompt naming the target object (examples: “cup”, “woman in the background”, “logo on the wall”).
- Choose copy_audio:
- true to preserve the original audio track
- false to output a silent video (useful if you’ll replace audio in post)
- Run the model, preview the result, and refine the prompt if needed.
Pricing
Billing rules (plain English):
- Minimum charge: $0.07 for any clip up to 5 seconds
- After 5 seconds: billed by duration in 5-second units at $0.07 per 5s
- Billing cap: durations over 600 seconds (10 minutes) are billed as 600 seconds
Effective rate:
- Standard rate: $0.014 per second
Reference prices (USD):
| Duration | Total Price |
|---|---|
| 5 s | $0.07 |
| 10 s | $0.14 |
| 20 s | $0.28 |
| 60 s | $0.84 |
| 600 s | $8.40 |
Notes
- Best results come from stable footage with clear object boundaries and minimal motion blur.
- Prompts work best when they are simple and unambiguous (“cup”, “person”, “backpack”).
- If removal looks imperfect, try making the prompt more specific (“white cup in her hands”, “person on the left”).
- Overlapping objects and heavy blur may require multiple passes or tighter prompts.
Related Models
- bria/remove-background — Fast, clean background removal for images, ideal for ecommerce product photos and design cutouts.
Video Eraser Prompt API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bria/video-eraser/prompt with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video Eraser Prompt below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bria/video-eraser/prompt" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"copy_audio": true
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("bria/video-eraser/prompt", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"copy_audio": true
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bria/video-eraser/prompt",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"copy_audio": true
}
)
print(output["outputs"][0]) # → URL of the generated outputVideo Eraser Prompt API — Frequently asked questions
What is the Video Eraser Prompt API?
Video Eraser Prompt is a Bria model for object / watermark removal, exposed as a REST API on WaveSpeedAI. Bria Video Eraser is an AI video inpainting model that removes unwanted objects, people, logos, and text from footage using natural-language prompts. It tracks targets across frames and reconstructs clean, temporally consistent backgrounds for edit-ready results. Ready-to-use REST 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 Video Eraser Prompt 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bria/bria-video-eraser-prompt.
How much does Video Eraser Prompt cost per run?
Video Eraser Prompt starts at $0.070 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 Video Eraser Prompt accept?
Key inputs: `prompt`, `video`, `copy_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-video-eraser-prompt.
How long does Video Eraser Prompt take to generate?
Average end-to-end generation time on WaveSpeedAI is around 55 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Video Eraser Prompt 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.