Stem Separation and What You Do With Each Half
Splitting a track into vocal and instrumental stems is the easy part. What each half is actually for — and a different tool entirely — is not.
7 min read
Subtitles, Text Overlays and Timed Overlays Are Not the Same Tool
Ask for 'captions' and you might get a transcript of your voiceover, a supplied hook line, or a burned-in overlay that never touches the audio.
8 min read
Text-Thread Scenes: Turning a Conversation Into Watchable Video
How to turn a text message exchange into a paced video scene: reveal timing, a reaction cutaway, and two different ways to voice the conversation.
7 min read
Three Ways to Find a Generation You Made Weeks Ago
search_my_media, fetch_user_generations, and browse_user_library cover non-overlapping ground — pick wrong and the agent returns nothing, not a redirect.
7 min read
Tool Schemas Are the New Prompt Engineering
An agent's output quality is bounded by how well its tools are described, not by how carefully you phrase the request. Our own definitions as the example.
9 min read
Type Contrast That Passes an Accessibility Review
Generated graphics fail contrast because the model optimized for looking good, not for a ratio. The actual thresholds, the exemptions, and a two-minute check.
9 min read
Uncrop Without Warping: Extending Backgrounds That Hold Up
Extended edges bend straight lines, duplicate hardware and drift in colour. How much unmasked context to feed a fill model, and where the platform crops anyway.
8 min read
Usage Rights in Creator Contracts: Organic, Paid, and the Perpetuity Trap
Organic posting rights aren't paid usage rights, and 'in perpetuity' isn't a formality. A plain-language walkthrough of the clause stack in creator contracts.
8 min read
Variable Fonts in a Brand System: Axes and Optical Size
One variable font file replaces a shelf of static weight cuts — and its optical size axis does something no weight dropdown can ever reproduce.
9 min read
The Vertical Ad Safe Zone Map: Where Platform UI Eats Your Creative
A placement guide for 9:16 ads: where TikTok and Reels UI covers captions, product shots, and text — and how to reframe one master render per platform.
7 min read
Voice Changing: Re-Voice a Recording Without Re-Recording
A guide read has perfect timing and the wrong voice. Re-voicing keeps the performance and swaps only the timbre — retyping the line throws both away.
8 min read
Web Delivery: AVIF, WebP, and Keeping Generated Images Fast
A model that generates at 4K doesn't mean your page should serve 4K. The compression numbers behind AVIF and WebP, and where each one actually wins.
7 min read
What a Grade Can and Cannot Rescue in AI Footage
A color grade redistributes existing pixel values — it fixes cast and continuity, not content errors, and can surface banding in compressed AI clips.
8 min read
Why Colors Shift Between Screen and Export
A brand red gets approved on screen, then ships looking orange somewhere else. The color pipeline broke between generation and export — here's exactly where.
8 min read
Why Prompt Adherence Collapses Around Keyframes
Near a supplied keyframe, models drift toward their own priors instead of the prompt — and escalating the prompt with more restrictions reliably makes it worse.
7 min read
Why Your Generated Clips Don't Match in the Timeline
Six clips that looked fine as previews come apart once cut together. The causes are resolution, frame rate, and bitrate mismatches between models, not your eye.
7 min read
Writing an AI Disclosure Line Nobody Scrolls Past
Once you have to disclose AI use, the disclosure becomes copy. Placement, wording and the specific ways a technically-correct label still fails.
7 min read
Seeds and Reproducibility in AI Generation
What seeds actually do in AI video and image generation, why fixed seeds don't guarantee identical outputs, and how creators use them to iterate.
7 min read
Hailuo 2.3 Prompting Guide
A practical Hailuo 2.3 prompting guide: prompt structure, motion and physics language, Fast vs Standard tiers, and fixes for common failure modes.
7 min read
How to Make ASMR Videos With AI
How to make ASMR videos with AI: sound-first production, generated trigger audio, macro close-up visuals, seamless loops, and mixing that keeps tingles.
7 min read
Building a Media Kit With AI (Images, Clips, Numbers)
Build a creator media kit with AI: the pages brands actually read, generating visuals and clips, presenting your numbers honestly, and keeping it current.
6 min read
Flux 3 Video Prompting: Native Audio and Long Takes
Flux 3 video prompting for native audio and long takes: layered soundscape cues, staging language, and first/last-frame prompts for continuous shots.
8 min read
How AI Music Generation Works
How AI music generation works for creators: audio tokens, why lyrics come out singable, what prompts control, and where generated tracks still break.
7 min read
How to Clip a Podcast With AI
Turn one podcast episode into 10+ clips with AI: moment selection, 9:16 reframing, timed captions, hook title cards, and a posting cadence that compounds.
7 min read