Product blog

Product blog

Product updates, field guides, and field notes—each with links to docs and the hub where relevant. High-level milestones also appear on the changelog.

  1. The all-in-one NSS Background Remover editor: layers, 3D scene, lifestyle composer, and AI suite on one pipeline

    Product highlight · Jun 9, 2026

    Inside the all-in-one NSS Background Remover editor: layers, 3D, lifestyle scenes, and a 90-tool AI suite

    A guided tour of the all-in-one NSS Background Remover editor: how layers, selection, adjustments, 3D, lifestyle scenes, the video editor, and the AI assistant fit on one on-device pipeline that never uploads your files.

    • Layers, 3D, lifestyle scenes
    • ~90 on-device AI tools
    • .nss-project saves, no upload

    NSS Background Remover

    Read
  2. Timeline of NSS Background Remover growing from a single cutout tool to a ~90-tool on-device AI suite

    Product highlight · Jun 8, 2026

    From cutout tool to a ~90-tool AI suite: the road to enterprise-grade background removal

    A product update tracing how the Background Remover grew from one tool into a full on-device AI suite, and the engineering discipline that kept it free, private, and reliable along the way.

    • ~90 client-side AI tools
    • Honest tiers + real CLIP vision
    • Reliability-hardened to v1.5.0

    NSS Background Remover

    Read
  3. The full NSS Background Remover story: on-device models, straight-alpha export, and the worker-isolation rebuild

    Product highlight · Jun 7, 2026

    How we built a background remover that runs entirely in your browser — and what it taught us about client-side AI

    The complete build story — privacy stance, models in the browser, straight-alpha export, the worker rebuild — and the lessons that came out of shipping real client-side AI.

    • Fully on-device AI
    • Straight-alpha, professional output
    • The rebuild that reshaped how we build

    NSS Background Remover

    Read
  4. Three model tiers — Lite, Standard, Pro — with their real download sizes and hardware requirements

    Field guide · Jun 5, 2026

    Honest AI tiers: Lite, Standard, Pro — sized in gigabytes, not hype

    Why naming real model sizes and recommending a tier your device can run beats promising everyone the heaviest model.

    • Lite 0 / Standard ~400MB / Pro ~2GB
    • recommendTier() probes WebGPU + memory
    • Delete downloaded weights any time

    NSS Background Remover

    Read
  5. Tracing a silent failure from symptom to undisposed model session to the worker-isolation fix

    Field guide · May 26, 2026

    Diagnosing a silent failure: the ONNX worker-session bug that broke tool execution

    A debugging story a developer hitting the same wall can learn from: the symptom, the trace, the root cause, and the structural fix.

    • Silent failure, no stack trace
    • WASM heap corruption from an undisposed session
    • Fixed by per-job worker isolation

    NSS Background Remover

    Read
  6. Capability detection choosing WebGPU or WebAssembly, with measured inference timings and a fallback path

    Field guide · May 25, 2026

    WebGPU vs WASM for client-side ML: what actually changed our inference speed

    WebGPU is faster; WASM is universal. Here is how a real tool uses both, and the measured difference it makes.

    • 2–5s WebGPU vs 8–15s WASM (RMBG-1.4)
    • Automatic capability detection
    • Fall back, then retry on GPU failure

    NSS Background Remover

    Read
  7. Before and after: tangled per-tool queues versus one canonical queue with isolated per-job workers

    Field guide · May 23, 2026

    When patches compound, rebuild: the queue and worker overhaul

    The real story of a compounding-patch trap, the decision to rebuild the approach, and the lesson about when patching becomes the problem.

    • When patches compound, rebuild
    • Per-job worker isolation
    • One canonical queue across all tools

    NSS Background Remover

    Read
  8. Batch queue feeding a single worker sequentially with per-item retry and ZIP output

    Field guide · May 22, 2026

    Removing backgrounds from 100 images at once without freezing the tab

    The engineering behind keeping the UI alive while the same tab runs a neural network on image after image.

    • Sequential, not parallel
    • Per-job worker isolation
    • Results delivered as a ZIP

    NSS Background Remover

    Read
  9. NSS Background Remover: on-device AI pipeline from image to straight-alpha PNG, no upload

    Product highlight · May 21, 2026

    NSS Background Remover: AI-powered, in-browser background removal — free forever, no signup

    A launch article on why NSS Background Remover exists, how in-browser AI changes the privacy equation, and what straight-alpha export means for professional design workflows.

    • On-device AI
    • True straight-alpha PNG
    • Batch up to 100 images

    NSS Background Remover

    Read
  10. Straight versus premultiplied alpha compositing math and the resulting clean edge versus dark halo

    Field guide · May 21, 2026

    Straight alpha vs premultiplied alpha: the export detail that breaks other tools

    The single most common reason a free cutout looks wrong in professional software, explained with the actual math and what we do differently.

    • The black-halo problem
    • alpha = round(mask × 255)
    • RGB of transparent pixels preserved

    NSS Background Remover

    Read