Tag
“webgpu”
9 posts
Technical Deep Dives··9 min readThe WebGPU Shader Bug That Broke Best Quality — A Debugging Postmortem
Best Quality background removal worked in some browsers and silently failed in others with a cryptic WGSL compile error. Here is the trail we followed to the root cause — a bug deep in a machine-learning runtime — and the one-line-idea fix.
Technical Deep Dives··9 min readfp32, fp16 and int8: What Model Precision Means for Your Cutouts
Fast or Best Quality? The real difference is how many bits each number in the model uses. Here's what fp32, fp16 and int8 do to your cutout's size, speed and edges.
Tutorials··7 min readWebGPU, Explained for Creators: Why Your Browser Can Suddenly Run Real AI
You keep seeing 'WebGPU' next to AI tools. Here's what it actually is, in plain language — what changed, why it matters for editing photos and video, and how to tell if your device has it.
Product & Mission··7 min readBrowser AI vs. Cloud API: Who Actually Sees Your Images?
When a tool runs AI in your browser, your files never leave the device. A clear comparison of client-side ONNX/WebGPU inference vs. cloud APIs — on privacy, cost, latency, and offline use.
Technical Deep Dives··6 min readWhy Our Best-Quality Background Remover Runs on WASM, Not WebGPU
WebGPU guarantees only 8 storage buffers per shader stage. BiRefNet's graph wants 33–65. That single number decides where our best-quality model runs — and why "just use the GPU" isn't an option.
Technical Deep Dives··6 min readWe Run the Model in Your Browser Instead of Our Server. Here's the Real Tradeoff.
Client-side background removal is a set of concrete engineering tradeoffs, not just a privacy slogan. What you gain (privacy, zero marginal cost, offline) and what we pay (download size, device variance) and how we manage each.
Technical Deep Dives··5 min readHow We Finally Proved Which GPU Path Our Models Actually Use
For dozens of update rounds we debated whether a slowdown meant our models silently fell back to WASM. We never knew — because nothing logged it. The one small telemetry probe that changed how we diagnose performance.
Product & Mission··8 min readWhy We Built a Background Remover That Runs 100% in the Browser
The technical and ethical reasons we chose to run all AI inference in the browser instead of on a server — WebGPU, ONNX, privacy, and what we gave up to get there.
Technical Deep Dives··10 min readHow AI Background Removal Actually Works
What's really happening when an AI model removes a background — segmentation models, ONNX, WebGPU, and why running in the browser is better than a cloud API for privacy.