MagicEraser.org (AI Background Eraser) · Background removal
Full-size export without login or ad interruptions has upfront credit costs; use depends on limited guest credits and cloud processing.
US-West (California, AS2914)
2048 × 2048 · PNG · Open native file ↗
Subsequent pricing and service checks are shown separately without altering historical scores.
One run does not establish all complex scenes, untested paid maxima or long-term uptime.
Plans & historical pricing
Web subscriptions, displayed top-ups and enterprise quote; USD · 2026-10-20
11 plan / billing-period records, all listed; — means that period is not recorded.
Verified 10,000 credits for $120 and 30,000 for $330, both one-time payments with non-expiring credits. The pricing page quantifies upscaling, restoration, editing and video use but not background removal; general credits are not asserted removal counts.
Verification has gaps; unknown prices and quotas are not inferred.
Cancellation, sources & verification record
Cancel anytime in account dashboard
Official plans and usage terms ↗ · 2026-10-20 Capture 1 ↗
Large top-up package selections ↗ · 2026-10-20 Capture 1 ↗ · Capture 2 ↗
Pricing recorded on the test date · 2026-10-16
10 Free Credits for guests without login; paid plans from ~$6.9/mo
Freemium + monthly/annual credit subscriptions
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- 2048×2048 (100.0% area retained)
- Attached file dimensions
- 2048 × 2048 · PNG
Read directly from the attached file; this does not establish free download availability at that size.
- Watermark
- No watermark
- Free allowance
- Guests receive 10 Free Credits without login; background removal costs 2 Credits per image (5 free 2048px transparent PNG exports)
- Account requirements
- No login required using the 10 initial Free Credits (Google/email sign-in also supported)
- Maximum specification record
- 2048×2048 (Guest no-login direct 2048×2048 RGBA PNG export, 100.0% pixel retention)
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Single-image page plus dedicated Batch Image Editor
- Manual refinement
- Supports post-cutout background blur slider and custom background replacement
Tested result & sample
Delivers crisp hair-edge matting (mad_band=0.0908, SAD(k)=41.38) with 99.87% foreground recall and an ultra-low 0.043% background leak, exporting a 4.78MB 2048×2048 RGBA PNG.
- Edge error MAD
- 0.0908 · Lower is better
- Global error SAD(k)
- 41.383 · Lower is better
- Foreground retention
- 99.870% · Higher is better
- Background residue
- 0.043% · Lower is better
These historical measurements describe alpha error at edges (MAD), total alpha error / 1000 (SAD), foreground retention and background residue. Low-resolution outputs are aligned to the reference under the original protocol; this does not imply a full-resolution export.
- Fixture
- anchor_bgremove_v1
- Recorded environment
- US-West (California, AS2914)
- Network-observed server wait
- 7 s
- End-to-end reference
- 14.6 s
Network wait includes round trips, queuing and polling error, not pure inference time. Local timings depend on the device; repetition counts are not standardized in legacy records.
Experience, rules & trust
- Disclosure
- Displays credit cost (2 Credits) and remaining free credits before upload
- Interaction
- Zero third-party ad banners or login walls; clicking "Download Transparent Image" immediately triggers native browser download.
- Entity record
- MagicEraser.org / LinoCut AI (ImgUpscaler Matrix)
- Origin
- US / APAC Independent AI Vision Team
- Domain history record
- 2023–2026
- Third-party tracking record
- Google Analytics · Aliyun SLS Web Tracking
- External information
- Consistent with its Object Remover, it offers guest-usable no-login credits with full-resolution unwatermarked downloads.
- Processing
- Cloud async segmentation pipeline (api-v2.imgupscaler.ai / magiceraser_remove_bg_v1)
- Retention statement
- Temporary signed OSS URLs expire after ~4 hours
A recorded statement does not verify deletion or all data-processing behavior.
Verifiable audit trail & evidence
Four SHA-256-verified stages link the benchmark fixture, same-run interface screenshots, native exported artifact and archived pricing sources.
anchor_bgremove_v1 · Inspect fixture & file inspector →
Captures entry rules, result view and export disclosure.
Official plans and usage terms (snapshot ↗) · Large top-up package selections (snapshot ↗)
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 85.4/100
Overall = honesty & reputation × 30% + capability × 70%. Component maxima follow this report’s rubric. List scores are rounded for display; original precision is retained here.
Scoring version 2.3.1 · Test fixture anchor_bgremove_v1
Honesty & reputation · 92/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 40 / 40 | Top navbar clearly shows 10 initial Free Credits for guests and the upload card states "Credits Required: 2 Credits" upfront; removes background without login and directly exports a 2048×2048 RGBA PNG (4.78MB, unwatermarked). | Evidence A → |
| Interaction restraint | 20 / 20 | Zero third-party ad banners or login walls; clicking "Download Transparent Image" immediately triggers native browser download. | Evidence A → |
| Background & reputation | 19 / 25 | Part of the ImgUpscaler / LinoCut AI visual tool matrix (sharing the api-v2.imgupscaler.ai backend), widely used for no-login image editing. | Evidence C → |
| Engineering & privacy | 13 / 15 | Submits async jobs (magiceraser_remove_bg_v1) over HTTPS and returns signed US-West OSS URLs (iudcbe0.pbsimgs.com); includes Google Analytics and Aliyun SLS telemetry. | Evidence B → |
Capability · 82.5/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 52.5 / 65 | Transition band error mad_band=0.0908 · Global SAD(k)=41.383 · Foreground recall 99.87% / Background leak 0.043% | Evidence A → |
| Deliverable specifications | 20 / 20 | True Alpha channel (8/8); Max deliverable spec: 2048×2048 (Guest no-login direct 2048×2048 RGBA PNG export, 100.0% pixel retention) | Evidence A → |
| Processing speed | 10 / 15 | Network-observed server wait: 7s (API mode: async; network upload 6.04s / end-to-end 14.6s shown for reference only, never penalized) | Evidence A → |
Legacy scores may include advertised maximum capabilities. Read tested output separately from paid capabilities. Records without matching tiers and scope are not ranked together.
Revisions & corrections
- 2026-10-16
Initial real-machine benchmark using anchor_bgremove_v1 synthetic GT and CDP network timing.