Text Prompts

When to Use

• Crowded scenes where default detection picks wrong subject.
• Product videos with specific object isolation needs.
• Character videos requiring accessory preservation.

Prompt Writing Tips

1. Use concrete noun first: person, dog, red car.
2. Add unique descriptors: clothing, color, position.
3. Avoid long narrative sentences.
4. If unstable, simplify prompt to core object description.

Request Example

curl -X POST https://api.removebgvideo.com/v1/jobs \
  -H "X-Api-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://cdn.example.com/input.mp4",
    "model": "pro",
    "text_prompt": "person wearing black hoodie",
    "background": { "type": "transparent" },
    "output_format": "webm",
    "auto_start": true
  }'

Good Prompt Examples

• person wearing red jacket
• golden retriever dog
• blue sports car
• wooden dining table
• anime character with green dress and staff

Quality Guardrails

• Prefer representative source clips when tuning model defaults.
• Keep input compression moderate to preserve edge details.
• Use explicit output format policy for transparent vs non-transparent workflows.
• Run A/B validation with the same clip set before changing defaults.

Implementation Checklist

1. Define payload schema validation in backend before forwarding requests.
2. Store model/output_format/background settings with each job record.
3. Add internal quality review for difficult scenes (hair, glass, motion blur).
4. Create runbook entries for model-specific failure cases.

Prompt Debugging Playbook

• Start with concise noun phrases, then add qualifiers.
• Avoid contradictory descriptors in one prompt.
• Use comma-separated target objects for multi-subject retention.
• Keep prompt stable across retries to isolate model behavior changes.

When to Use Text Prompts

Text Prompts belongs to the Guides section and covers use prompt-guided segmentation with pro model.

The page is written for developers and operators who need predictable video background removal behavior in production, not just a one-off demo request.

• Use this guide when text prompts decisions affect output quality, processing cost, or user-facing workflow design.
• Test guidance on representative videos rather than only short demo clips.
• Record the chosen model, background, output format, and quality notes with each processed job for later debugging.

Implementation Notes

Before you promote this workflow, test it with at least one short clip, one longer clip, and one visually difficult clip from your actual product or customer segment.

For support and debugging, persist the original input reference, selected model, output format, credit usage, and final job status alongside your internal user or project id.

• Do not judge quality from a single frame; inspect motion, hair, hands, transparent edges, and fast turns.
• Do not compare model outputs using different source compression levels.
• Do not change production defaults without a rollback path and a known sample set.

Related Documentation

FAQ