How to choose a caption font from the registry
A guessed font name doesn't error — it just doesn't do what you asked. What each font category does to legibility at caption size on moving footage.
7 min read
Cliffhanger Engineering for Serialised Verticals
Cliffhangers aren't a writing flourish in a 60-second vertical, they're the mechanism that gets episode two watched. The cut has to land early, not late.
7 min read
CMYK Reality Check: Why Prints Land Duller Than Screens
A brand blue that's perfect on every screen comes back muddy from the printer — not a printer error. The color was never reachable in ink to begin with.
9 min read
Consistency Collapse: Diagnosing Drift Between Shots
'It doesn't look consistent' isn't one problem. It's four — identity, wardrobe, set and lighting — each with a different cause and a different fix.
8 min read
Content Credentials on Design Files: What C2PA Records
A Content Credential is not a watermark — it is a signed manifest of assertions about origin and edits. What is actually inside one, and what survives editing.
7 min read
Which Content Credentials survive a real pipeline
A Content Credential is two different bindings doing two different jobs. Walk a file through trims, re-encodes and uploads and see which one actually survives.
8 min read
Continuation prompting from the last four seconds
Continuation prompting explained: hand a model the end of an existing clip plus an instruction for what happens next, and extension becomes direction.
7 min read
Conversational Video Editing With Gemini Omni Flash
How Gemini Omni Flash's edit loop lets you fix, restyle, and iterate on a clip across turns without breaking continuity, using Versely's Edit endpoint.
7 min read
Cover Versions of Tracks You Already Own
An AI cover doesn't compose a new song — it reinterprets a track you supply. That single mechanical fact is why the whole question is source rights.
7 min read
How to prompt crash zooms and whip pans
Why whip pans and crash zooms break text-to-video prompts, what Wan 2.2 docs reveal about how camera motion is learned, and when to switch to motion transfer.
9 min read
Creative diversification on Meta and TikTok
Meta reports 32% more efficient direct-response outcomes from diversification. TikTok wants at least four different creatives per ad group, refreshed weekly.
7 min read
Cron Schedules for Recurring Content Series
Post every Tuesday has to become five specific fields somewhere. The cron syntax, four everyday translations, and two prerequisites that fail silently.
7 min read
Crop Safety: Designing Once for 1.91:1 Through 4:5
A nested safe-zone method for composing one master image that survives every crop Instagram Feed accepts, from 1.91:1 landscape to 4:5 portrait.
7 min read
Day-to-Dusk and Season Swaps for Property Photography
Twilight conversion used to be a paid add-on and a slow Photoshop job. What changes when it's a plain-language instruction, and what disclosure it now needs.
7 min read
Design-Native Models vs General-Purpose Image Generators
Recraft V4 and Riverflow 2.0 were built with designers, not for beauty contests. Feature tags predict fit for real deliverables better than any Elo score.
7 min read
Designing for Viewers Who Turned Their AI Dial Down
TikTok and Pinterest now let users control how much AI content they see. That turns audience AI-fatigue from a vibe into an algorithmic constraint.
7 min read
How to resume a stalled render without restarting
Restarting a stalled multi-scene render throws away every completed scene. The real state machine, the stuck threshold, and what resume actually resets.
9 min read
Digital Replica Rights Are Turning Into Property
US federal law is moving toward treating likeness as a licensable right, not just a tort you sue over after the fact. What that shift means for consent.
8 min read
Disclosure Stacking: Ad Labels, AI Labels, and Paid Partnership Tags Together
A per-platform checklist for posts that need three disclosures at once: FTC material connection, platform paid-partnership toggles, and AI-generated labels.
8 min read
Ducking Music Under a Voiceover
The most common audio flaw in AI-assembled video is a music bed that won't get out of the way. What actually fixes it, and the stems escape hatch.
7 min read
Edit Models vs Generate Models: A Selection Table
71 text-to-image, 42 edit-image, 30 image-to-image models — and only 3 do all three. A job-first way to pick the right one instead of shopping by brand.
7 min read
Editing Copy Inside a Finished Graphic
Changing a price or date inside a finished graphic is an edit job, not a generation job — and mixing the two up is why files get rebuilt from scratch.
8 min read
ElevenLabs Music v2 and Dubbing v2, explained
ElevenLabs shipped chunk-based Music v2 and a performance-preserving Dubbing v2, then retired its v1 speech models. What changed, and how to match briefs.
7 min read
Emotional Story Ads: Narrative Arcs That Outsell Discounts
When emotional story arcs beat feature lists and discount codes, how to storyboard one with AI in an afternoon, and the claim-hygiene rules that still apply.
8 min read