Use cases
Worked examples on Sume's catalog Formats and endpoints: product video and photography, try-on, app and product ads, logo animation, and more.
Start with Ready-made Formats for product video: the Sume Format catalog
How many clips for a 10-minute faceless video? Timeline slot math
A 10-minute faceless video fits Timeline 1.0 comfortably: up to 200 slots, a render near $1.00, and limits on fades and single-pass renders to plan around.
Korean captions on product clips: use korean-ad, not slam
slam, punch and tiktok-green have no Hangul glyphs and return 400 on Korean copy. Use korean-ad with language ko for Korean product clips; $0.20 a job.
Find product moments in a live-commerce replay and trim them out
Run one transcript on a live-selling replay, find the sentences where each product is pitched, then cut each range with video-trim at $0.02 a clip.
Live replay highlight reel in one render: detach once, no trims
Detach a live replay's audio once ($0.01), then build a 30-second highlight reel in one Timeline render using audio parts and source_in. No per-clip trim jobs.
Pin a product card on a live-selling clip with one overlay call
POST /v1/timeline-1.0/compose with operation overlay pins a product still at bottom, center or top of a live-selling clip for $0.02. Layout keys and limits.
Launch teaser from product shots: Gemini Omni Flash reference images
Feed up to 10 product references to gemini-omni-flash-1.1 on Sume, address them as IMAGE_REF_0 in the prompt, and get a 3-10 second teaser with native audio.
Re-roll one shot in a stitched film without redoing the rest
Regenerate a single bad shot, swap its source_url in the Timeline 1.0 video array, and re-render the cut for $0.10 per output minute. The other shots stay.
Recast a video longer than 30 seconds: trim, recast, rejoin
H3 Max Recast takes 5 to 30 seconds of source. For a 90 second video on Sume, probe it, trim ranges, recast each at 768p, then plan the join. Cost math inside.
Review a creator clip's transcript before reusing it as a paid ad
Get a creator clip's transcript for $0.01 per audio minute with video inspect, then flag risky claims with your own word list before the clip becomes an ad.
Score a multi-scene video with AI music: tempo, key, lead instrument
How to brief Sume Music for a video with several scenes: one consistent score or contrasting cues, with tempo, key and lead-instrument rules from the docs.
Sketch plus face photo to a thumbnail with GPT Image 2.5
Send a rough layout sketch and a portrait as two references and ask GPT Image 2.5 for a 16:9 thumbnail. The prompt, a 1280x720 Sume request and what to verify.
Trim a long video then caption the clip: two Sume jobs in order
Cut a moment from a long recording with video-trim, then burn captions on the new MP4. Why the order matters, what each job costs, and which URL goes where.
Upload 15 YouTube Shorts at a time: prepare the batch with Sume
YouTube's upload page lets you pick up to 15 Shorts at once. Prepare 15 correctly sized clips with Sume trim jobs, one idempotency key each.
YouTube automatic captions not available: what to do instead
YouTube lists silence, overlapping speakers and poor audio as reasons auto captions fail. Burn your own with Sume cues or a script_text-aligned caption job.
YouTube inauthentic content rule: a faceless channel checklist
YouTube's monetization policy targets mass-produced, generic content. What a faceless channel should vary per episode, and which Sume steps hold your input.
AI-written script on a public-interest topic: Article 50 text label
Article 50(4) text labels cover published public-interest text with no human review or editorial control. What counts as review, per the Commission.
AI Act marking exemption for B2B and industrial output: how narrow
The Commission FAQ says a narrow Article 50(2) marking exemption is envisaged for B2B or industrial outputs, with conditions in the guidelines. What it lists.
AI Act Article 50 fines: up to EUR 15M or 3%, and who enforces it
The Commission's Article 50 FAQ says fines can reach 15 million euros or 3% of worldwide turnover, enforced mainly by national market surveillance authorities.
AI Act Article 50 for non-EU providers: output used in the EU
The Commission FAQ says providers outside the EU are subject to the AI Act if their system's output is used in the EU. How it defines provider and deployer.
Can one avatar UGC ad change location mid-video? One scene only
Sume's avatar video renders one avatar and one shared scene per final video. For a second location, make two jobs and join them with a Timeline 1.0 render.
Character turnaround sheet by API: front, profile, back views
Make a turnaround sheet by API: render the front view, then send it as a reference for profile and back. Google's 360-view method, and the Sume request.
EU AI icon: embedded in the video or a UI overlay, and when reshared
The Commission says the EU AI icon should be embedded in the content unless an equivalent like a UI overlay exists, and be visible on reshare or download.
EU AI icon licence: free, no attribution, not proof of compliance
The Commission's EU AI icons are free with no attribution, but using one does not prove compliance, and a non-signatory using one does not signal adherence.
Meta AI Reels translation: who can use it, and the 1,000-follower rule
Per Meta, Reels translation is free for Facebook creators with 1,000 followers or more and for all public Instagram accounts where Meta AI is available.
Not signing the EU transparency code: what you must show instead
The Commission says non-signatories must show their Article 50 measures are adequate, may face more information requests, and are assessed by each authority.
Auto-select creative assets missing in TikTok Ads Manager? Why
TikTok limits auto-selected creatives to Smart+ app promotion and select lead gen advertisers; a July notice widens lead gen. Check, then self-supply.
TikTok auto-selected creatives: the five exclusion filters
TikTok lets you exclude auto-selected videos by source, creator, caption text, date or single video. Batch your clips by date so one rule retires a round.
TikTok auto-selected creatives not adding my new videos: why
After you publish, TikTok keeps adding new creator content but not new videos from your own content. Add them by editing ad settings; batch the variants first.
TikTok Auto-Selection for lead gen: what to upload as a UGC clip
TikTok added Auto-Selection to Lead Generation campaigns. It draws on brand uploads, creator content and AI content, so upload several 9:16 clips, not one.
Translated with Meta AI label: how viewers turn Reels dubbing off
Meta labels every translated Reel Translated with Meta AI. A viewer picks Don't translate in the audio and language section of the three-dot menu to opt out.
YouTube AI disclosure: AI backdrop and own-voice clone examples
YouTube lists cloning your own voice and extending a backdrop as edits needing no AI disclosure. What else is on that list, and what is not.
Does YouTube's AI label hurt reach or monetization?
YouTube's help page says disclosing AI content won't limit a video's audience or monetization eligibility. What it says about skipping disclosure instead.
Zalando AI distortions: a checklist to run before upload
Zalando names three kinds of AI distortion it can reject: wrong article, implausible setting, inconsistent model. A checklist to run on generated images.
Zalando apparel model views: same model, shoes on, sleeves shown
Zalando's apparel guide for model views: same model and styling across views, shoes on, full-length sleeves, simple styling. What to put in an AI prompt.
Zalando image rejection 117 and 123: too few views, a mannequin
Zalando rejects articles for missing images (reason 117) and visible mannequins in mandatory views (reason 123). Duplicates do not count. What to regenerate.
Zalando image size: ask for 2000x2880, an exact 1:1.44
Zalando wants 1:1.44 JPEG portraits, best practice 1801x2600. Sume image_size takes multiples of 16, so 2000x2880 is an exact 1:1.44. Request it with jpeg.
Zalando jewellery packshot: lower third, symmetry, back view
Zalando's jewellery guide: primary packshot in the lower third of the grid, a back view showing fasteners, no upside-down logos. A prompt checklist for Sume.
Zalando packshot grid: article at about 80% of the frame, centred
Zalando's apparel and shoes grid puts the article at about 80% of the frame, centred; bags sit in the lower third. How to ask for that framing on Sume.
Zalando required images per article: 3, 2 or 1, then a batch plan
Zalando needs 3 images for apparel, accessories and shoes, 2 for home, 1 for beauty and others. A per-SKU plan for generating the missing views on Sume.
Zalando shoe packshot: left shoe pointing left, laces tied, centred
Zalando's shoes guide: primary packshot as catalogue view, left shoe pointing left, laces tied, centred. How to write the edit prompt on Sume.
Amazon Ads Video Generator: 8-second clips, 6 options; what next
Amazon's Video Generator returns six eight-second options for U.S. advertisers. For a longer or non-Amazon product ad, here is the Sume route and its limits.
China penalized CapCut and Dreamina over AI labels: what to check
China's CAC penalized CapCut, Maoxiang and Dreamina AI over AI labels in April 2026. What it means if your video tool serves viewers in China.
China platform AI labels: confirmed, possible and suspected
China asks platforms to sort content as confirmed, possible or suspected AI. What triggers each label and what a video team can do about it.
Event recap: trim dead pauses from a talk with inspect and trim
YouTube's coming editing assistant promises to trim pauses. Until then, find silent gaps in a talk from transcript segments and cut keeper ranges with Sume.
Flow's 50 daily credits don't roll over: plan a production week
Flow refreshes 50 free credits a day after first use and drops what you skip. How to plan a week of clips, and how a Sume USD balance behaves instead.
Flow monthly credits by Google AI plan: how many clips fit
Flow gives 200, 1,000, 10,000 or 25,000 bonus credits a month by plan. What that buys in Veo 3.1 and Gemini Omni Flash clips, and how a Sume balance differs.
Korea AI label tiers: invisible watermark vs visible for deepfakes
Korea's AI Basic Act allows invisible watermarks for obvious AI content like animation, but deepfakes need a visible label. How to tell which tier a clip is.
Korea AI Basic Act grace period: when do 30 million won fines start?
Korea's AI Basic Act took effect in January 2026 with a grace period of at least a year before fines of up to 30 million won. What to prepare now.