Your hook is a frame, not a line
The opening frame carries more hook load than the opening line. What clip-level data shows, the sound-off case, and a first-frame audit for your last 30 posts.
9 min read
Your image came back with a watermark you never added
Hallucinated stock marks come from training data, not the platform. Prompt changes that suppress them, plus a clean removal pass when they appear.
9 min read
Your image-to-video clip barely moves
A clip that reads as a photo with drift is an underspecified motion brief. Write one subject action and one camera move, then fix the source frame.
9 min read
Your ducking pumps instead of breathing
Pumping is a release-time problem, not proof sidechain was wrong. Attack, release and depth settings that hide the duck behind the voice.
9 min read
Your prompt was blocked. How to rewrite it
Most prompt blocks come from a few trigger patterns, not the idea. Isolate the phrase, rewrite it, and know when to switch models instead.
9 min read
Your reference image got cropped on upload
Some pipelines hard-crop uploaded references to the target ratio without warning. Pre-pad to that ratio yourself so the crop has nothing to take.
9 min read
The subject teleports halfway through the clip
Position snaps come from independently sampled segments with no shared anchor. First-last-frame conditioning lets motion flow through the join.
9 min read
Your generated subject never blinks
An unblinking subject is the tell that survives every other fix. Schedule eye behaviour in the prompt, or chain short clips at natural blink points.
9 min read
Your TTS mispronounces brand names
Invented and non-English names are the TTS failure case. Phonetic respelling that works across engines, and which providers take pronunciation markup.
9 min read
The upscaler changed your subject's face
A generative upscale redraws identity. Keep face denoise at or below 0.35, mask the face out of a hotter pass, and check a 100 percent crop before you commit.
9 min read
The model added dialogue you never wrote
Native-audio models treat 'no talking' as a cue to talk. Convert every negative into a positive audio state, with worked before-and-after prompts.
9 min read
Your voiceover sounds muddy under AI music
AI music beds crowd the same 250–500Hz band as speech. Carve that range, set a level relationship, and apply them in the right order.
9 min read
What YouTube's AI disclosure does not cover
YouTube exempts animation, beauty filters, colour work, effects, your cloned voice, captions and audio repair. Decide in one pass if a video needs the label.
9 min read
Where YouTube puts your AI label
Since May 2026, photorealistic AI labels sit below the long-form player and overlay Shorts. Unrealistic and minor edits stay in the expanded description.
9 min read
YouTube auto-labels AI from C2PA metadata
YouTube applies AI labels from three sources you don't fully control. Know which ones fire automatically before you decide what the upload toggle is for.
9 min read
YouTube measures growth against your own channel
Two YouTube surfaces compare a video to your own recent uploads rather than to the platform. Build the baseline that makes those comparisons readable.
9 min read
YouTube YPP thresholds for AI channels
You need 1,000 subs plus 4,000 watch hours or 10M Shorts views. Shorts-feed views never count toward watch hours.
10 min read
YouTube's Off-Putting Content Rule, Decoded
YouTube's second non-monetisable bucket judges the reaction a video is built to produce. The formats that trip it, and the edits that pull one back.
8 min read
YouTube Shorts length and resolution limits
Shorts cap at three minutes and 1080p. A hard delivery ceiling changes what generation resolution is for, and turns downscaling into a quality decision.
8 min read
How YouTube Shorts Revenue Sharing Works: The 45% Split
YouTube pays creators 45% of allocated Shorts revenue. One track sends half to the Creator Pool; two tracks send one third. Music does not change your 45%.
9 min read
Shorts views that earn no revenue
YouTube runs two counters on every Short: the public one and the payable one. Six categories of view sit in the first and never reach the second.
8 min read
The 30-Second Single Take: AI Video's Duration Race
Seedance 2.5 and Wan 3.0 chase 30-second single takes, Flux 3 ships 20s with audio. Why duration is hard to ship, and how to hit 30s on Versely today.
7 min read
A Client Review Loop Built on Previews and Share Links
Generation is fast. Client approval isn't. A review loop built from free previews, no-login share links, and a QC pass before anything gets sent.
7 min read
A Diagnostic Tree for Generations That Come Back Wrong
A decision tree for AI generations that come back wrong: what to change based on exactly what you see in the output, not what you originally asked for.
7 min read