Silent plate then score
Generate silent, score with music after, when dialogue is not the point. Native audio is optional, not mandatory.
6 min read
Wan 2.6 audio vs Wan 2.7
Wan v2.6 text-to-video can ship native audio. Wan 2.7 catalog rows may not. Read the row, not the family name.
6 min read
Snapchat Spotlight will not recommend wholly AI video
Snapchat said it will no longer recommend wholly AI-generated videos in Spotlight. The generate can still exist; the recommendation slot is what moved.
7 min read
A character sheet before the first video credit
Lock face, wardrobe, palette in stills. Video credits are the expensive way to discover the character drifted.
6 min read
Dreamina is not the only way to run Seedance
Arena entries are named dreamina-seedance-2.x. The model is callable elsewhere. You do not need ByteDance's consumer app to use 2.5.
5 min read
Grok Imagine when the destination is X
When the post lives on X, Imagine's look and the native sharing path can be the point. It is not the general video engine.
6 min read
The Kling app versus Kling 3 on a shared bill
The consumer app is one model family and one subscription. An aggregator bill lets you fail over when Omni is the wrong job.
5 min read
Luma Ray 3: HDR when audio is someone else's job
Luma Ray 3, launched 18 September 2025, makes native 16-bit HDR video at 1080p for grading. On Versely, Luma runs as Ray 3.2 and Ray 2, in standard SDR.
6 min read
Native audio versus TTS on the same brief
If the model can speak in-shot, do not generate silent and slap TTS on unless you need a locked brand voice.
6 min read
Runway Gen-4.5 is control, not a one-click model
Motion brush, camera, world consistency. Weak on native audio and arena Elo. A director's tool, not a volume engine.
6 min read
Sora 2 API ends September 24: reroute
Sora app ended 26 April 2026. API ends 24 September 2026. Dialogue to Veo 3.1, 30s identity to Seedance 2.5, motion to Kling 3, talking stills to Happy Horse.
6 min read
Which social platforms actually pay for AI video
Earning on social is a counterparty question, not a posting-volume question. Who signs the cheque on YouTube, TikTok, Instagram, X, Snapchat and Threads — and which income model that points to.
8 min read
X automated means: a person still publishes
X withholds Original Content Rewards when a post is created or posted using automated means. Publish a clip you reviewed. An auto-posted firehose fails.
7 min read
A scoring rubric for comparing video models
A weighted five-axis rubric with written 1-5 anchors for every point, so a model bake-off produces a number you can defend a week later.
9 min read
A 20-prompt suite for testing any video model
Twenty short prompts, each isolating one known failure axis, so a new model's weaknesses show up in an hour instead of halfway through a client project.
10 min read
Agent routing or picking the model yourself
Three job types where an agent's model choice predictably goes wrong, and how to pin a named model in the brief without giving up routing everywhere else.
9 min read
Directing gaze and micro-expression on a face
Emotion words return a stereotype. Eyeline, blink timing and independent brow movement are directable as physical actions — and here is where prompting stops.
9 min read
Fast-motion subjects and the models that survive
Subject speed breaks video models before camera speed does. A per-frame overlap test that predicts limb doubling, plus the shot design that buys real headroom.
9 min read
Fluid, fire and smoke: where video models diverge
Pours, flame and volumetric smoke fail in three different ways. How to rank them, and a rule for what to generate, what to composite, and what to cut.
9 min read
Grain, flare and vignette against the AI sheen
Generated footage reads wrong because imperfection is absent, not detail. A finishing order for grain, vignette and flare, and the amounts that hold up.
9 min read
What HappyHorse's 38-second render claim means
Alibaba quotes ~38 seconds per 1080p HappyHorse 1.1 clip on one H100. What a hardware-conditioned figure predicts about a hosted queue, and what it can't.
9 min read
The face changes when the character turns
A single front-facing still cannot constrain a profile, so identity collapses on the turn. Build a multi-angle sheet, and keep the turn as a cut.
9 min read
Muse Video ranks fifth and nobody can use it
Meta's Muse Video sits fifth on Arena's text-to-video board and has never shipped. A four-question filter that strips unusable models out before you plan.
8 min read
Nine specs a model page should publish
The nine facts that decide whether a video model fits a workflow, what each omission actually costs you, and how sparse most published model records really are.
9 min read
Related topics
AI VideoBrand Video Marketing245Short Form Video240Content Creation220AI Video Generator213Content Marketing167Social Media Strategy128Image To Video101Brand Growth100Captions66Credits64Video Editing59AI Advertising58Digital Marketing58Seedance 2 555First Last Frame54AI Disclosure50Video Generation48AI UGC47Viral Video Strategy47Character Consistency46Business Video45Instagram Reels44VEO 3.142Content Strategy40Ideogram V440Short Form39Team Productivity39UGC Ads39Burned In Captions38Native Audio38Text To Image37Voice Cloning37Flux 336Text Overlay36Text To Speech35Caption Styles34Marketing Automation34Text To Video34Vidu Q334YouTube Shorts34Post Production33Image Editing32UGC32Workflows32AI Lipsync31Compliance31Image Generation31Video SEO31Voiceover28Youtube28Reference To Video27TikTok Marketing27Prompting26Qwen Image 326Workflow26Accessibility25API25Seedream 5 Pro25Article 5024Tiktok24Trending Videos24Retention23Sora 223Usage Rights22Model Selection21Prompt Engineering21Brand Consistency20Faceless YouTube20Stills20Video Prompting20AI Music19AI Music Generator19Audio Mixing19Youtube Monetization19Aspect Ratio18Continuity18Disclosure18Safe Area18Talking Head18AI Content Pipeline17AI Video Workflows17Auto Captions17Brand Kit17C2pa17Creative Testing17Creator Economy17Eu AI Act17Likeness Rights17Motion Control17Product Video17Client Contracts16Hooks16Kling 3.016Quality Control16Seedance16Wan 2.716Agent15AI Content Label15AI Video Pricing15Audience Retention15Color Grading15Content Credentials15Grok Imagine15Kling 3 Turbo15MCP15AI Content Workflow14AI Dubbing14AI For Creators14Brand Safety14Camera Control14Inpainting14Localization14Reference Images14Temporal Consistency14Typography14Wcag14Agency Operations13AI Video Editing13Content Repurposing13Copyright13Frame Rate13Sound Design13Suno13Talking Head Video13Versely Agent13Ypp13AI Disclosure Rules12AI Image Generator12Automation12Batch Generation12Dubbing12Likeness12Product Photography12Production Workflow12Prompt Adherence12Synthetic Media12Thumbnails12Watch Time12Ypp Health12