BIRME · Image upscaling
BIRME is one of the rare free tools that runs AI super-resolution entirely client-side via in-browser WebGPU/WASM without requiring an account. In our live test, it upscaled a 1024px input to a full 2048x2048 watermark-free native PNG in 60.3s, achieving an edge correlation of 0.6668 that significantly outperforms traditional bicubic interpolation while providing uncompromising zero-upload privacy.
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
BIRME 100% free client-side batch image processing and compression · 2026-11-01
Smart crop, format conversion (JPG/PNG/WebP/AVIF), quality compression, watermark, AI background removal and upscaling；Pure client-side execution; very large batches may consume significant browser memory；Permanently free, no renewal；Perpetual access
1 plan / billing-period records, all listed; — means that period is not recorded.
All batch resizing, compression, AI background removal, and upscaling are 100% free with voluntary donation support and zero paid plans.
Cancellation, sources & verification record
Cancellation and refund terms unverified
BIRME Official Studio ↗ · 2026-11-01 Capture 1 ↗
Pricing recorded on the test date · 2026-11-01
100% Free (Unlimited / No watermark / Voluntary donation)
Free
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- 2048 × 2048 (PNG · 4.0x full-resolution direct export)
- 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
- Completely free, no quota limits, pure client-side WebGPU processing
- Account requirements
- All features available directly without registration or login
- Maximum specification record
- 2048 × 2048 (PNG · 4.0x full-resolution direct export)
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Supports arbitrary batch processing limited only by local device memory and GPU VRAM
- Manual refinement
- Not recorded or not verified
Tested result & sample
BIRME AI Enhance runs purely offline via browser WebGPU/WASM, upscaling 1024x1024 to 2048x2048 with an edge correlation of 0.6668, delivering significantly better detail than bicubic interpolation.
- Fixture
- anchor_upscale_v1
- Recorded environment
- US-West (California, AS2914)
- Local processing record
- 60.34 s
- End-to-end reference
- 60.34 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
- Page transparently outlines all resizing and AI enhancement parameters
- Interaction
- Not recorded or not verified
- Entity record
- BIRME Project
- Origin
- United Kingdom
- Domain history record
- Founded in 2013
- Third-party tracking record
- Google Analytics
- External information
- Continuously operating for 13 years since 2013, renowned for pure client-side privacy.
- Processing
- Pure client-side WebGPU/WASM in-browser offline neural inference, zero uploads
- Retention statement
- Data never leaves device, destroyed immediately upon tab closure
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_upscale_v1 · Inspect fixture & file inspector →
Captures entry rules, result view and export disclosure.
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 93.6/100
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_upscale_v1
Honesty & reputation · 96/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 35 / 35 | Explanation unavailable | Evidence A → |
| Interaction restraint | 28 / 30 | Explanation unavailable | Evidence A → |
| Background & reputation | 18 / 20 | Explanation unavailable | Evidence A → |
| Engineering & privacy | 15 / 15 | Explanation unavailable | Evidence A → |
Capability · 92.5/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 60.5 / 65 | PSNR vs 2048px GT: 26.97 dB · SSIM: 0.8897 · Edge Gradient Correlation: 0.6668 · High-Freq Sharpness Ratio: 0.5048 · Calibration Plate PSNR: 16.08 dB | Evidence A → |
| Deliverable specifications | 20 / 20 | Clean unwatermarked export (8/8); Free scale factor: 4x (2048 × 2048 (PNG · 4.0x full-resolution direct export)) | Evidence A → |
| Processing speed | 12 / 15 | Network-observed server wait: 60.34s (API mode: client_side; end-to-end 60.34s 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
- 2026-11-01
Initial real-device live benchmark using Mode A super-resolution anchor (anchor_upscale_v1) evaluating guest usability and objective metrics via local WebGPU.