Background Removal Models

​

Model Comparison

​

Quick Comparison

​

When to Use Each Model

​

videobgremover-original (Default)

• Highest quality segmentation with precise edge detection
• Complex scenes with multiple objects or complex movement
• Professional output for client deliverables
• Challenging scenarios that require the best possible accuracy

• Professional video production
• E-commerce product videos with complex products
• Videos with multiple subjects or objects
• Content with complex movement or camera motion

​

videobgremover-light

• Fast processing (1.5x faster than original)
• Cost savings (25% cheaper)
• Face cam or talking head videos (single person content)
• High volume processing where speed matters

• Face cam videos and presentations
• UGC (user-generated content) with people talking
• Social media content with single subjects
• Quick prototypes or drafts

​

Usage Examples

​

Using Models via SDK (High-Level)

import { VideoBGRemoverClient, Video, RemoveBGOptions, Prefer, Model } from 'videobgremover'

const client = new VideoBGRemoverClient(process.env.API_KEY!)
const video = Video.open('./video.mp4')

// Option 1: Use light model (faster, cheaper)
const optionsLight = new RemoveBGOptions(Prefer.WEBM_VP9, Model.VIDEOBGREMOVER_LIGHT)
const foreground = await video.removeBackground({ client, options: optionsLight })

// Option 2: Use original model (highest quality)
const optionsOriginal = new RemoveBGOptions(Prefer.WEBM_VP9, Model.VIDEOBGREMOVER_ORIGINAL)
const foreground = await video.removeBackground({ client, options: optionsOriginal })

// Option 3: Use default (original model)
const optionsDefault = new RemoveBGOptions(Prefer.WEBM_VP9)
const foreground = await video.removeBackground({ client, options: optionsDefault })

​

Using Models via API Client (Low-Level)

import { VideoBGRemoverClient } from 'videobgremover'

const client = new VideoBGRemoverClient(process.env.API_KEY!)

// Create job
const job = await client.createJobUrl({ video_url: 'https://example.com/video.mp4' })

// Start with light model
await client.startJob(job.id, {
  model: 'videobgremover-light',  // 25% cheaper, 1.5x faster
  background: {
    type: 'transparent',
    transparent_format: 'webm_vp9'
  }
})

// Wait for completion
const result = await client.wait(job.id)

​

Using Models via cURL

# Create job
JOB=$(curl -s -X POST https://api.videobgremover.com/v1/jobs \
  -H "X-Api-Key: $API_KEY" \
  -F "file=@video.mp4")

JOB_ID=$(echo $JOB | jq -r '.id')

# Start with light model (faster, cheaper)
curl -X POST https://api.videobgremover.com/v1/jobs/$JOB_ID/start \
  -H "X-Api-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "videobgremover-light",
    "background": {
      "type": "transparent",
      "transparent_format": "webm_vp9"
    }
  }'

​

Pricing Examples

• Original model: 30 × 1.0 = 30 credits
• Light model: Math.ceil(30 × 0.75) = 23 credits (7 credits saved, 23% cheaper)

• Original model: 120 × 1.0 = 120 credits
• Light model: Math.ceil(120 × 0.75) = 90 credits (30 credits saved, 25% cheaper)

• Original model: 300 × 1.0 = 300 credits
• Light model: Math.ceil(300 × 0.75) = 225 credits (75 credits saved, 25% cheaper)

​

Default Behavior

• ✅ API: Defaults to videobgremover-original
• ✅ SDK: Defaults to videobgremover-original
• ✅ Web UI: Uses videobgremover-original

​

Model Selection Tips

​

Next Steps