See your options side by side
Choose one task and 2–4 tools. Compare pricing, output, test results and trust.
Test scope & comparison notes
These are recorded facts, not a unified ranking. Tested tiers and scope are not consistently recorded. Read pricing with its date and timing with its conditions. Privacy observations reflect visible flows and statements, not a security audit.
Cross-task capability coverage across selected products
Each product is scored independently per task edge; switch tasks below while keeping shared products selected| Task edge | Inpaint-web | Nero AI | Switch / compare |
|---|---|---|---|
| Background removal | Not tested in topic | 80/100 2000 × 2000 · PNG | Compare in task topic → |
| Image compression | Not tested in topic | 88/100 2048 × 2048 · PNG | Compare in task topic → |
| Image upscaling | Not tested in topic | 84/100 2048 × 2048 · PNG | Compare in task topic → |
| Object removal | 83/100 2048×2048 (Full-Res Unwatermarked PNG) · Historical description; output not attached | 77/100 2000 × 2000 · PNG | Active task |
| Image generation | Not tested in topic | 91/100 1024 × 1024 · PNG | Compare in task topic → |
| Photo restoration | Not tested in topic | 79/100 JPEG · Output attached | Compare in task topic → |
Select at least 2 tools to compare
You can also filter a task page first, then compare your shortlist.
Browse this task →| Criterion | Inpaint-web (Open-Source Browser WebGPU Inpainting) Object removal 83/100 Seven-aspect task score Free open-source, login-free and ad-free on-device processing exports full size; complex bookshelf repairs show blocky texture and need inspection. Tested export 2048×2048 (Full-Res Unwatermarked PNG) · Historical description; output not attached Historical test · 2026-10-16 | Nero AI Object Remover Object removal 77/100 Seven-aspect task score Smart Brush cleanly selects and removes all three signs in one pass and exports a watermark-free 2000×2000 PNG for 2 free credits, though inputs above 2000px are auto-resized and async queue wait reached 71.3s. Tested export 2000 × 2000 · PNG Historical test · 2026-10-22 |
|---|---|---|
| Pricing & rules | ||
| Pricing plans | Inpaint-web in-browser open-source object removal and upscaling tool · 2026-10-21 Plan · source date Monthly / one-time Annual bill / period Quota & limits Inpaint-web Open-Source Free2026-10-21 ↗ Free Free Free Free open-source tool without login; unlimited local in-browser object removal and 4x upscaling with full-resolution unwatermarked export. 1 plan / billing-period records, all listed; — means that period is not recorded. Open-source free web tool (MIT License) powered by client-side WebGPU and WebAssembly. Models run locally in the browser with no registration, paid plans, or usage limits. Cancellation, sources & verification recordCompletely free open-source project with no accounts or billing. Inpaint-web official web workspace ↗ · 2026-10-21 Capture 1 ↗ | Nero AI web plans (Free / Standard / Yearly promo / Business); USD · 2026-10-21 Plan · source date Monthly / one-time Annual bill / period Quota & limits Free2026-10-21 ↗ Free Free Free 5 free guest runs without login; 10 one-time credits per registered account (max 1000×1000px upload, 5 images/batch; 2× costs 1 credit, 4× costs 2 credits). Standard Monthly (300 credits)2026-10-21 ↗ USD 21.95/month — Monthly 300 credits/month (promotional USD 21.95/month, regular USD 24.99/month); up to 4000×4000px upload, 30 images/batch, priority processing, and 8× upscaling. Standard Yearly (3,000 credits/yr)2026-10-21 ↗ — Annual price not verified Annual 3,000 credits/year; promotional banner displays USD 7.66/month equivalent. Public page displays only the 7.66 USD/month equivalent without showing the annual invoice total before login. Business2026-10-21 ↗ Contact sales Quoted Quoted Custom credits and pricing (up to 200 images/batch, highest priority, API processing, and dedicated server). 4 plan / billing-period records, all listed; — means that period is not recorded. The official pricing page and credit table state that guests get 5 free runs and registered Free accounts receive 10 one-time Nero Credits (Standard/Photo/Anime 2× costs 1 credit/image, 4× costs 2 credits/image, paid-only 8× costs 4 credits/image). Standard monthly is USD 21.95/month promotional (regular USD 24.99/month, 300 credits/month). The yearly promo banner displays only "7.66 USD per month" (3,000 credits/year) without printing the annual invoice total before login, so the annual total is marked unverified. Verification has gaps; unknown prices and quotas are not inferred. Cancellation, sources & verification recordCancel anytime by turning off auto-renewal in account settings (remaining credits expire at the end of the billing period); FAQ states refunds are not allowed once Nero Credits have been used. Nero AI official pricing, credit consumption table, and FAQ ↗ · 2026-10-21 Capture 1 ↗ |
| Free & trial allowance on the test date | 100% free and open-source; unlimited local browser inference and full-resolution exports | Each object removal run consumes 2 Nero Credits; inputs above 2000×2000 are auto-resized to 2000×2000 on the free tier (Pro supports 4000×4000) |
| Cancellation & refunds | Completely free open-source project with no accounts or billing. | Cancel anytime by turning off auto-renewal in account settings (remaining credits expire at the end of the billing period); FAQ states refunds are not allowed once Nero Credits have been used. |
| Disclosure of costs & limits | Completely free and open-source with zero hidden charges | Discloses the 2000px resize rule and 2-credit cost before processing |
| Task quality | ||
| Measured fixture results | Not verified | Not verified |
| Fixture findings | Processes locally with full-size export; smooth areas worked better than complex bookshelf texture. | All three plaques are 100% erased with natural wooden counter and bookshelf reconstruction (inpaint_psnr_db = 13.29 dB) and high unmasked fidelity (unmasked_psnr_db = 32.92 dB, SSIM = 0.9161) (53.0/65). |
| Original historical observation | Inpaint-web runs the MIGAN inpainting model locally in the browser via ONNX Runtime Web, erasing all 3 signs directly on the 2048×2048 image and exporting a full-size PNG without uploading a single byte to any server. Smooth wood surfaces restore cleanly, while complex bookshelves show lightweight client-model texture patterns. | Smart Brush accurately snapped to all three signs and removed them cleanly with natural bookshelf and wood-grain reconstruction (inpaint_psnr_db = 13.29 dB, unmasked_psnr_db = 32.92 dB); main trade-offs are the free-tier 2000×2000 resize cap and a 71.3s async queue wait in this run. |
| Suitable uses · historical assessment | Privacy-conscious users who require 100% local in-browser processing (zero cloud upload) and unlimited free 2048px+ unwatermarked exports | Users with images up to 2000×2000 who want clean multi-region object/text removal and watermark-free PNG export |
| Result & output evidence | No native output obtained; the preview does not establish final export quality. | |
| Delivery capabilities | ||
| Recorded export specifications | 2048×2048 (Full-Res Unwatermarked PNG) · Historical description; output not attached · Check watermark record No native output is attached; check the evidence for specification and watermark claims. | 2000 × 2000 · PNG · No watermark in test |
| Historical specification note · not an official maximum | 2048×2048 (Full-Res Unwatermarked PNG) | 2000×2000 (auto-resized from 2048×2048 under the free 2000px cap) |
| Watermark observation | None (100% watermark-free) | Watermark-free (2000×2000 RGBA PNG native export) |
| Batch & API | Supports multi-step history snapshots, hold-to-compare original, and built-in local 4x upscaling | Supports Rectangle and Smart Brush selection, post-removal Refine, and commercial API (/ai-api) |
| Recorded free-tier dimensions | Not verified | 2000 × 2000 |
| Attached file dimensions | Not verified | 2000 × 2000 · PNG |
| Speed & reliability | ||
| Timing observation | Recorded local processing time: 13.8s · End-to-end reference: 13.8s | Network-observed server wait: 71.3s · End-to-end reference: 71.31s |
| Date & fixture | 2026-10-16 · anchor_inpaint_v1 · US-West (California, AS2914) | 2026-10-22 · anchor_inpaint_v1 · US-West (California, AS2914) |
| Repeated tests & reliability | No standardized repetition count, success rate or variability range is recorded. | No standardized repetition count, success rate or variability range is recorded. |
| Interaction experience | ||
| Account requirements | No login in this test | No login in this test |
| Sign-in methods | No registration or login required; works immediately in browser | 5 free guest runs; signing in with Google or email grants 10 Nero Credits |
| Manual adjustment | Not verified | Manual erase / adjustment recorded in the historical flow |
| Interaction observations | Minimalist open-source workspace with zero popups, ads, or email gates; automatically preserves step-by-step history thumbnails along the top bar (02_workspace.png, 03_download.png). | Offers both Rectangle and Smart Brush selection tools; selecting all three signs with Smart Brush and clicking Remove provides a clean "Original PNG: 2000 × 2000 px" vs "AI Removed PNG: 2000 × 2000 px" split comparison and a one-click watermark-free Download button (02_result.png, 03_download.png). |
| Background & reputation | ||
| Service lifecycle notice | Not verified | Not verified |
| Operator | Inpaint-web Open Source Project (lxfater) | Nero AG |
| Recorded origin | Open-Source Developer Community (GitHub: lxfater/inpaint-web) | Karlsruhe, Germany |
| Domain history record | 2023–Present (Flagship WebGPU client-side AI vision project) | 1995–present |
| Background & reputation assessment | Popular GitHub open-source project lxfater/inpaint-web powered by ONNX Runtime Web / WebGPU with fully auditable MIT-licensed source code. | Official online AI object removal tool by Nero AG (Karlsruhe, Germany, founded 1995). |
| External reputation record | Not verified | Not verified |
| Engineering & privacy | ||
| Processing location | On-device processing | Uploaded for cloud processing |
| Third-party tracking record | Not verified | Not verified |
| Engineering & privacy assessment | 100% local browser-side WebGPU/WASM execution: once the ONNX model is cached in IndexedDB, all pixel processing happens inside local browser memory with zero server uploads. | Executes multi-region inpainting via an asynchronous cloud task queue (POST /api/v2/task ImageRemover + GET /api/v2/task/status polling) with a single-sample server wait of 71.3s, returning a watermark-free 2000×2000 RGBA PNG (6,876,668 bytes). |
| Retention statement | This flow runs locally; post-close deletion not independently verified | Explicit retention period unconfirmed; inspect policy record |
| Evaluation basis | ||
| Pricing transparency | 34 / 35 100% free open-source tool (01_landing.png): zero registration, zero login, unlimited runs, and no subscription paywalls. Clicking Download exports a native 2048×2048 unwatermarked PNG (03_download.png). | 27 / 35 The landing page (01_landing.png) provides direct upload; after uploading the 2048×2048 test anchor, the workspace explicitly discloses that the free tier resizes inputs above 2000×2000 to 2000×2000 (Pro supports 4000×4000) and labels "2 Nero Credits will be used" beneath the Remove button alongside remaining credits in the header (02_workspace.png). |
| Interaction restraint | 29 / 30 Minimalist open-source workspace with zero popups, ads, or email gates; automatically preserves step-by-step history thumbnails along the top bar (02_workspace.png, 03_download.png). | 25 / 30 Offers both Rectangle and Smart Brush selection tools; selecting all three signs with Smart Brush and clicking Remove provides a clean "Original PNG: 2000 × 2000 px" vs "AI Removed PNG: 2000 × 2000 px" split comparison and a one-click watermark-free Download button (02_result.png, 03_download.png). |
| Background & reputation | 14 / 20 Popular GitHub open-source project lxfater/inpaint-web powered by ONNX Runtime Web / WebGPU with fully auditable MIT-licensed source code. | 19 / 20 Official online AI object removal tool by Nero AG (Karlsruhe, Germany, founded 1995). |
| Engineering & privacy | 14 / 15 100% local browser-side WebGPU/WASM execution: once the ONNX model is cached in IndexedDB, all pixel processing happens inside local browser memory with zero server uploads. | 12 / 15 Executes multi-region inpainting via an asynchronous cloud task queue (POST /api/v2/task ImageRemover + GET /api/v2/task/status polling) with a single-sample server wait of 71.3s, returning a watermark-free 2000×2000 RGBA PNG (6,876,668 bytes). |
| Task quality | 49.5 / 65 Masked GT Reconstruction (21.5/30: structural PSNR=14.63dB · SSIM=0.4166) · Unmasked Fidelity (17.5/20: zero pixel alteration outside brush strokes) · Texture Continuity (10.5/15: smooth wood table restoration, though complex bookshelf spines show stylized MIGAN block patterns) | 53 / 65 Masked region reconstruction (21.5/30: inpaint_psnr_db = 13.29 dB, all 3 high-contrast signs 100% erased) · Unmasked fidelity (19.0/20: unmasked_psnr_db = 32.92 dB, SSIM = 0.9161, zero out-of-mask alteration) · Texture coherence (12.5/15: natural bookshelf spines, wooden counter, and hanging vines) (53.0/65) |
| Deliverable specifications | 20 / 20 Exports native 2048×2048 full-resolution unwatermarked PNG without login (20/20) | 19 / 20 Watermark-free 2000×2000 PNG native export (8/8); capped by the free tier 2000×2000 input limit, downscaling the 2048×2048 master to 2000×2000 (95.37% pixel area retention; Pro supports 4000×4000) (11.0/12) |
| Processing speed | 9.5 / 15 Client-side ONNX/WASM 2048×2048 local inference takes ~13.8s per stroke with 0.0s network upload overhead | 3 / 15 2026-10-22 same-run single-sample network timing: ImageRemover core task (r9 POST /api/v2/task -> r41 GET /api/v2/task/status) server wait 71.3s (slow >20s) (3.0/15) |
