Roadmap

Core AI pipeline

ORMBG and BiRefNet inference — no signup, no upload, no server.

Image editor

Brush erase/restore, edge refinement, feather, smooth, expand, decontaminate.

Video editor

Playback, grade, trim, overlay, and export for processed video.

Video upscaler

Single-pass ffmpeg Lanczos 2× and 4× upscaling for video clips, fully in-browser.

Video filter

Cinematic LUT presets applied frame-by-frame to video.

Video stabilizer

Browser-based camera shake reduction.

AI image upscaler

2× and 4× super-resolution. Runs in your browser.

Image filter

Cinematic LUT presets with intensity control and open-in-editor.

WASM auto-retry

When GPU inference fails, all workers automatically retry with WASM backend.

17 utility tools

Format converter, PNG optimizer, image compressor, resizer, canvas extender, rotate, grayscale, ICO creator, add background, color picker, color extractor, compare formats, metadata remover, check transparency.

Manual image adjustments

Brightness, contrast, saturation, and temperature controls in the image editor — composable with filter presets.

Enhanced edge quality

CPU-side guided filter + hair/fur soft alpha preservation + erosion — fast "Clean Edges" in ~1s without re-running AI inference.

33 image filter presets

Expanded filter library: Sepia, Teal Orange, Bleach Bypass, Cross Process, Neon Noir, Pastel Dream, Infrared, B&W Soft, B&W Hard, Fade Black, Fade White — all selectable by name in the image editor.

Color-key background removal

Automatic solid-color detection for graphic content — faster than AI, no model download required.

Smart edge decontamination

Lab ΔE post-processing pass removes background color spill from subject edges without eroding fine hair or fur detail.

Upscaler quality improvement

CPU-side unsharp mask post-pass for AI-upscaled images — sharper output without a larger model.

First-run model caching

Pre-download AI models on first visit with a progress indicator — subsequent sessions start instantly with no wait.

Mobile optimization

Pointer-event canvas (touch + stylus), pinch-zoom, collapsible bottom tab bar on mobile viewports.

Transparent material support

Post-pass algorithm for glass, plastic, and acrylic — Lab ΔE background detection, glass/specular preservation, partial alpha smoothing.

Lifestyle scenes in the editor

Product photo → remove the background → composite the cut-out onto 14+ lifestyle scene templates (oak tabletop, marble studio, dark slate, kitchen counter…) with edge-aware blending → PNG/WebP/AVIF export. Built into the image editor background panel.

Sitewide queue overhaul

Cancel and restart work correctly across all tools — no page refresh needed. Workers are terminated immediately on cancel; next queued item auto-starts.

Image upscaler minimum resolution

2× always outputs at least 2048 px on the longest edge; 4× always outputs at least 4096 px. Tiny inputs are pre-scaled so the AI model always produces useful output.

Video stabilizer duration fix

Fixed output being 2–3× longer than input. Frames are now collected as blobs before encoding — seek overhead no longer inflates video length.

Offline model pre-download

First PWA launch shows a one-time prompt to cache the Fast model plus both Best Quality runtime variants (~336 MB) for offline use via the Cache API.

Video utility tools

Format converter, compressor, resizer, canvas extender, rotate, metadata remover, and format comparison — in-browser video utilities. AudioContext removed from all play-through tools to eliminate freeze-on-large-files.

ORT heap-corruption fix

Reclassified WASM heap-corruption ORT errors as non-recoverable. Per-job worker isolation now works correctly — Best Quality mode retries spawn a clean WASM session instead of looping in a corrupt heap.

Stabilizer over-smooth fix

Smoothing window reduced from 5–60 frames to 3–25 frames at max strength (80% default → ~20 frames vs. old ~49). Scene-cut detection resets the trajectory accumulator at hard cuts.

Image upscaler instant-mode sharpening

Unsharp mask (strength 0.45) applied after Lanczos instant mode — same post-pass as AI mode. Per-tile 90 s health check terminates stalled workers early.

BiRefNet heap-corruption fix

Definitive WASM heap fix: session.dispose() in all reload paths including the stale-session detection block. Deterministic ONNX input key (session.inputNames[0]) replaces brute-force key loop. Best Quality mode now reliable.

Edge quality — topology-aware cleanup

Fast mode preserves thin structures while reclaiming connected background gaps and tightening only uncertain edge pixels.

Per-tile upscaler timeout

The Swin2SR tile loop has a 30s per-tile Promise.race() guard. Stalled tiles surface as errors rather than hanging indefinitely.

Per-tool how-it-works pages

22 individual tool guides at /how-it-works/[slug] — 3-step technical walkthroughs, FAQ, related tool links, and HowTo structured data for rich results.

Landing pages upgraded

All tool and editor landing pages now include the 4-point "Why it's different" section and a contextual CTA — consistent standard across all 30+ pages.

Video utility unmount cleanup

All 6 video utilities abort their RAF draw loops when the user navigates away — no wasted CPU from background processing after page exit.

PWA icon fix

Added <link rel="apple-touch-icon"> and <link rel="icon"> to <head> — installed app on iOS, Android, and desktop now shows the correct NSS logo instead of a generic browser icon.

Before/after comparison on key pages

Interactive drag-to-reveal comparison slider on the homepage and image upscaler pages. Demo SVG image pairs at /demo/.

All-in-one landing page (/all-in-one)

New comprehensive landing surfacing all editors + tools alongside the existing BG remover landing at /. Header link added; SEO preserved on /.

Shared layer architecture

Image editor and video editor both use the same <LayersPanel> with multi-file drop, opacity, blend modes (12), reorder, lock, duplicate, and keyboard shortcuts (Ctrl+J / Shift+]/[ / Delete).

3D mode (image + video editors)

Three.js installed and dynamic-imported. Flat 3D plane + depth-displaced relief mesh (reuses existing depth model) + lighting/material/background controls + click-to-select gizmo + 4-second 360° orbit recorder → WebM. Available in both editors.

AI subject targeting (R-SAM)

Press S in the image editor and click any subject — colour-space flood-fill with edge cleanup isolates that region. Tolerance shared with Magic Wand slider.

Batch video processing ZIP (R-BVID)

The Video Upscale queue now shows "Download all as ZIP" when 2+ jobs are complete. Single click downloads all results.

More languages (R-LANG)

Spanish, German, Portuguese, Japanese — 75+ translated UI strings per locale via next-intl. Runtime resolver: cookie > Accept-Language > en. Footer LocaleSwitcher.

PWA icon unification (A1)

src/app/icon.svg + icon.png + apple-icon.png all unified on the purple-sparkle brand mark. Manifest URLs versioned (?v=4) to bust OS install cache. SW cache bumped v3→v4; icon paths served network-first.

Floating quick-actions toolbar

Photoshop-style draggable toolbar above the canvas (image + video editors). Undo / redo / zoom / filter dropdown / background dropdown / adjust sliders / export buttons / shortcuts. Position persists in localStorage.

Layer-aware export (EXPORT-V2)

Export panel now has Pipeline mode (clean mask + filter + background) and Canvas-snapshot mode (captures everything visible including overlay layers). Per-layer inclusion checklist with Select all / Select none.

Tools utility expansion in editor

UtilityToolsPanel in the image editor gained palette extraction, transparency check, colour picker, PNG optimizer, metadata stripper, and one-click PNG/WebP/AVIF/JPG export — every utility callable from inside the editor without leaving.

Real photography template library (R-PHOTO)

All 14 lifestyle templates ship with themed backdrops generated per-slug via scripts/fetch-lifestyle-photos.mjs (image.pollinations.ai, deterministic seeds). LifestyleComposerZone HEAD-checks each photoUrl and falls back to the SVG mockup automatically. Drop a curated studio shot of the same filename into /public/templates/lifestyle/photos/ to override any individual backdrop.

Best Quality on native WebGPU

Best Quality background removal now runs BiRefNet through onnxruntime's native WebGPU engine, fixing a generated-shader crash (i32(vec4<u32>)) that made it fail silently on some GPUs. A mask-validation gate re-runs on WASM whenever a result comes back suspiciously empty.

One-time-use by design

Removed project saving, auto-save session restore, recent files, and live collaboration. Nothing persists after you close the tab — a stronger privacy promise than storing things carefully.

Google AdSense Auto Ads

Site advertising via Google AdSense Auto Ads on marketing and content pages. The editors stay completely ad-free.

Editor panel clipping fixes

Layers and resize panels no longer clip on the right edge, and their menus now portal out of overflow-hidden containers. The video editor gained a filter-intensity slider to match the image editor.

Sharper upscales — no seams or soft edges

Joint-bilateral alpha upsampling snaps cut-out edges to the sharpened colour, and feathered tile seams remove the faint grid AI upscaling could leave across large images.

Stabiliser playback-speed fix

Stabilised clips now play at the original speed and duration — the renderer normalises frame timing so output no longer runs slow, with audio kept in sync.

Honest video upscaling

The video upscaler now uses a stronger denoise + Lanczos + adaptive-sharpen chain, and the docs were corrected to stop implying an AI video mode that never existed.

SEO + AI crawlability

Breadcrumbs sitewide, an expanded sitemap, an explicit AI-crawler allow-list in robots.txt, and an llms.txt summary so assistants can discover and index the tools.

AI photo colouriser

Colour black-and-white and sepia photos on-device — a realistic neural model (opt-in download) plus instant palette styles, as a standalone tool and inside the image editor with undo. Honest about the limit: it makes a plausible guess, not a record of the true colours.

Video background removal

A recurrent matting engine removes a video background entirely in-browser without frame-to-frame flicker. Export transparent WebM, a composited MP4, or a PNG sequence.

GIF background removal, rebuilt

Per-frame cut-outs for animated GIFs with a solid-background fast path, edge dithering and matte colour for GIF's on/off transparency, and an APNG export for true soft alpha.

Video object remover overhaul

Click-to-segment (SlimSAM), draw-a-box, or one-click plate blur/removal in the video editor. Remove, Blur, or Pixelate — edits persist on the timeline and can be undone and replayed.

Metadata inspector

Reports camera, GPS, colour-profile, and AI-provenance metadata (C2PA, Stable Diffusion params), and strips all / AI-only / a custom selection losslessly without re-encoding your pixels.

Upscaler source routing

A Source selector routes photos, flat graphics/logos, and pixel-art down the right super-resolution path, with an honest cap so tiny sources are not stretched into mush.

Share, without uploading

A page-level share menu across articles, guides, and tools, plus result-image sharing that hands a finished file to your device's share sheet locally — never uploaded to us.

Production-walkthrough fixes

ZIP export no longer crashes, the editor's AI 2×/4× works again, the video resizer shows real progress, the base layer's blend mode is unlocked, and lifestyle scenes composite correctly behind a clip.

Faster video decoding (WebCodecs)

Decode video frames through the browser's native VideoDecoder instead of seeking frame by frame — several times faster for background removal and object editing on longer clips.

Sharper video mattes

Use the matting model's foreground estimate to correct edge colour on cut-outs, so fringes pick up less of the old background — the same idea already used on still images, applied per frame.

Object remover that re-locks onto moving subjects

Periodically re-run click-segmentation on keyframes so a tracked object stays selected through rotation and scale changes, not just straight-line motion.

Object removal (inpaint) in the image editor

Bring the video object remover's LaMa inpainting to the still-image editor — brush over an unwanted object and have the background filled in.

Mobile editor responsive layouts

Beyond the current mobile tab bar — full responsive layouts for narrow viewports across every editor panel, so the image and video editors are genuinely usable on a phone.

WebCodecs export for the video editor

Frame-accurate encoding via the browser's native VideoEncoder — faster, sharper exports with exact timing, generalising the offline renderer already built for the stabiliser.

Photoreal scene generation

An opt-in, on-device diffusion pass (SD-Turbo image-to-image) to generate a matching backdrop behind a cut-out subject, instead of only compositing onto preset scenes — gated on device capability and download size.

Audio stem separation

Split a video's audio into vocals / music / other stems in-browser (Demucs) so you can mute or isolate a track before export.

Smooth slow-motion (frame interpolation)

Generate in-between frames (RIFE) to make slowed-down clips fluid instead of stuttery.

Short-clip AI video enhancement

An opt-in AI super-resolution pass for short video clips, on top of the current filter-based upscaler — gated on device capability and download size.

Real-time video effects

Apply colour grades, overlays, and blur to video output in real time via WebGL shader passes.

Group + clipping mask layers

Bundle several layers under a group with shared opacity / blend mode / lock, plus adjustment-layer clipping masks for non-destructive corrections.