Leonardo.Ai (Universal Upscaler · Pro Precise) · Image upscaling
Credit costs and sizes are shown upfront with clear comparison controls; free output is 2× and images are public by default, with private mode paid.
US-West (California, AS2914)
No native export attached; page screenshot evidence only
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 individual and default three-seat team plans; excludes API · 2026-10-20
10 plan / billing-period records, all listed; — means that period is not recorded.
The app payment panel confirms personal annual prices of $120/$288/$576, differing from earlier rounded monthly equivalents on the marketing site. Public plans permit paid users to buy top-ups without quoting pack prices or per-removal token cost. Unlimited relaxed generation does not establish unlimited removal.
Verification has gaps; unknown prices and quotas are not inferred.
Cancellation, sources & verification record
Self-serve cancellation in account settings
Official plans and usage terms ↗ · 2026-10-20 Capture 1 ↗ · Capture 2 ↗
Official app annual payment selection ↗ · 2026-10-20 Capture 1 ↗ · Capture 2 ↗ · Capture 3 ↗
Pricing recorded on the test date · 2026-10-16
Free $0/mo (150 Tokens/day) · Essential $10/mo (billed yearly, 8,500 Tokens/mo) · Premium $24/mo
150 daily free resetting tokens + Monthly/annual subscriptions
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- 1024×1024 (2.0x · Unwatermarked high-quality JPG · 271.9 KB)
- Watermark
- None (Completely unwatermarked)
- Free allowance
- Free accounts receive 150 daily resetting Fast Tokens; Universal Upscaler (Pro · Precise · 2x) costs 5 Tokens per image (~30 free upscales per day)
- Account requirements
- Requires Google / Apple / Microsoft / Email login
- Maximum specification record
- 1024×1024 (2.0x · Costs 5 Free Fast Tokens · Unwatermarked JPG)
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Supports Legacy / Ultra / Pro modes, Precise / Creative styles, and production REST API
- Manual refinement
- Not recorded or not verified
Tested result & sample
PSNR=25.77 dB · SSIM=0.9605 · edge_corr=0.6507 · hf_ratio=0.7040: unlike diffusive enhancers that heavily alter lighting and geometry, Leonardo's Aurora Precise mode injects rich high-frequency detail while preserving 0.9605 SSIM structural consistency.
- Fixture
- anchor_upscale_v1
- Recorded environment
- US-West (California, AS2914)
- Network-observed server wait
- 14.2 s
- End-to-end reference
- 16.8 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.
No native export is attached. Screenshots show the visible page, but do not independently establish export properties or file validity.
Experience, rules & trust
- Disclosure
- Displays 'Upscale 🪙 5' and target output '1024 × 1024px 1 MP' upfront before clicking Upscale (Screenshot ②)
- Interaction
- Clean `/universal-upscaler` studio workspace with zero credit-card trial popups or countdown banners, offering Compare, Side-by-side, and Single inspection views.
- Entity record
- Leonardo Interactive Pty Ltd (Canva)
- Origin
- Sydney, Australia
- Domain history record
- 2022–Present
- Third-party tracking record
- Not recorded or not verified
- External information
- Not recorded or not verified
- Processing
- Cloud Aurora Precise / Creative / Ultra super-resolution cluster (5 Tokens per 2x upscale, ~14.2s server inference)
- Retention statement
- Free tier upscales are stored in cloud history and public by default; paid tiers unlock private generations and deletion
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.
Page screenshot evidence only
Official plans and usage terms (snapshot ↗) · Official app annual payment selection (snapshot ↗)
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 77.7/100
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 · 81/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 29 / 35 | Transparent token pricing and deliverable specs: the right-hand panel clearly displays 'Output: 1024 × 1024px (1 MP)' and 'Upscale 🪙 5' (consuming only 5 of the 150 daily free Fast Tokens, see Screenshot ②), and exports a completely unwatermarked 1024×1024 image. | Evidence A → |
| Interaction restraint | 24 / 30 | Clean `/universal-upscaler` studio workspace with zero credit-card trial popups or countdown banners, offering Compare, Side-by-side, and Single inspection views. | Evidence A → |
| Background & reputation | 18 / 20 | Developed by Leonardo Interactive Pty Ltd (Sydney, Australia; acquired by Canva in 2024), powered by its proprietary Aurora Precise / Creative super-resolution models. | Evidence C → |
| Engineering & privacy | 10 / 15 | Free plan creations and upscales are public by default; private mode requires upgrading to Essential ($10/mo). | Evidence A → |
Capability · 76.3/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 52.8 / 65 | PSNR vs 2048px GT: 25.77 dB · SSIM: 0.9605 · Edge Gradient Correlation: 0.6507 · High-Freq Sharpness Ratio: 0.704 · Calibration Plate PSNR: 14.57 dB | Evidence B → |
| Deliverable specifications | 15 / 20 | Clean unwatermarked export (8/8); Free scale factor: 2x (1024×1024 (2.0x · Costs 5 Free Fast Tokens · Unwatermarked JPG)) | Evidence B → |
| Processing speed | 8.5 / 15 | Network-observed server wait: 14.2s (API mode: async_poll; end-to-end 16.8s shown for reference only, never penalized) | Evidence B → |
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-browser evaluation using Mode A synthetic degradation ground-truth anchor (anchor_upscale_v1: 512px -> 2048px GT).