shopify image pipeline

IMGFLOW

upscale · compress · webp · isnet bg removal · smart resize · 100% local, zero api
GIT : ABIR614
0 processed
Drop images here
JPG · PNG · WEBP · BMP — multiple files supported
PRESET
First run downloads model · cached in browser forever
↑ higher = harder cut, fewer stray pixels
0 = crisp · higher = softer edge
PNG preserves full alpha · WebP is smaller for Shopify
Auto: crop if larger · extend if smaller
Auto: crop if larger · extend if smaller
Per-axis smart detection vs. ratio-preserving fit
Used when cropping dimension(s)
Where image sits when extending / fitting
Softens extension seam (0 = sharp)
Applies to extended / letterbox areas
#ffffff
SOURCE
TARGET
Smart Auto-Resize — Per Image, Per Axis, Never Distorted
Each image is compared against your target per axis independently. Wider than target → object-aware crop (saliency, not just faces). Narrower → seamless canvas extension via directional gradient sampling (no banding). Exact match on an axis → passthrough for that axis. Switch to Proportional Fit to never crop — only letterbox/pillarbox. Set Fill → Transparent to keep extended areas as alpha (saves as PNG). AI Fill uses LaMa ONNX (Carve/LaMa-ONNX, Apache 2.0) — a 51M-parameter inpainting model running 100% in-browser via onnxruntime-web (WebGPU → WASM fallback). First run downloads ~208 MB and caches it in IndexedDB forever.
🧠
ISNet Background Removal — ONNX Runtime, 100% Local
Powered by @imgly/background-removal running ISNet-General-Use in-browser via ONNX Runtime. First run downloads ~45 MB model weights (cached forever after). A live progress bar shows per-file download status. Choose ISNet FP16 for faster inference or Quint8 for the smallest download. Output as WebP for Shopify or PNG to keep full lossless transparency.
QUEUE 0 files
No images queued · drop files above to begin