Month archive
Posts from August 2026
6 articles, newest first.
- Tutorials··10 min read
How to Remove and Replace Objects in Photos Without Uploading Them
A precise browser-local workflow for selecting an object, refining its mask, reconstructing the space it occupied, and placing a real replacement asset as an editable layer — without sending the photo to a server.
- Tutorials··11 min read
From Long Video to Captioned Highlights: A Browser-Local Workflow
Turn a long clip into reviewed highlight ranges, transcribe its latest edited audio, correct timed captions, and export a shorter captioned result while keeping the work on your device.
- Technical Deep Dives··8 min read
Why Sharpening a Cutout Draws a Halo Around Fur
Upscale a cutout of a long-haired pet and a bright rim appears along the fur. The model did not do it — an alpha-blind sharpening pass did, by averaging in the black that sits behind every transparent pixel. Here is the mechanism, the fix, and exactly what the numbers behind it were measured on.
- Tutorials··9 min read
Restoring an Old Family Photo, End to End: Face First, Then Colour
A complete in-browser workflow for a scanned family print — neutralise the paper, rebuild the face with GFPGAN (one per run), then colourise with DDColor. Including the part that decides whether you should use the result at all: what 'restore' does and does not recover.
- Technical Deep Dives··9 min read
Which Blurs Can Be Recovered, and Which Are Simply Gone
Camera shake, focus miss, subject motion and noise all look like 'blurry' and only some of them are reversible. Here is what a deconvolution model can actually put back, the resolution trade the tool makes to run in a browser tab, and how to tell in advance whether a photo is worth the attempt.
- Tutorials··9 min read
Writing Alt Text That Actually Helps — and Where an AI Caption Fits
Most images ship with no alt text because there are a hundred of them and no time. A captioning model that runs on your device fixes the blank-page problem but not the hard part. Here is the decision that comes before the writing, what the model can and cannot know, and the edit pass that turns a caption into alt text.