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
Lecture slides beside the speaker: one Timeline compose shot per slide
Timeline compose stacks one still and one video in a frame, up to 300 seconds a shot. Make one stack per slide, then join them in Timeline 1.0.
Listing photo tour in 16:9 and 9:16 from one slot list (Timeline 1.0)
Stills are static holds in Timeline 1.0. Keep one video[] list of listing photos and change only output size and fit for a 16:9 and a 9:16 tour.
Meta Creator Marketing Hub: what Sume can do to a creator clip
Meta's Creator Marketing Hub unifies Creator Marketplace and Partnership Ads. Sume cannot join it, but it can trim a creator clip and burn captions on it.
Microsoft Teams app icon 192x192: generate at 1024 and resize
Teams wants a 192x192 PNG color icon, a perfect square with the logo in a 120x120 safe area. Generate 1024x1024 on Sume with GPT Image 2.5 and resize.
Podcast audio to a 45-second teaser video with Timeline source_in
Timeline 1.0 takes an audio spine with a source_in in-point and a still as a static hold, so a podcast excerpt plus cover art renders as a video with no editor.
A 15-second 'previously on' recap from one episode with source_in
Detach an episode's audio once, then list three moments twice in one Timeline 1.0 render: video[].source_in for picture, audio.parts source_in for sound.
Shopify Canvas: prepare a hero image and loop for your store
Shopify Canvas, announced October 1, 2026, is a visual store design workspace with Sidekick. Prepare a wide hero and a tall clip with Sume now.
Shopify first sale in a day: a same-day product video plan
Shopify says nearly 10% of new shops sell within a day. A same-day plan with Sume: one hero image, one 4 to 30 second clip, then a poll, with no promises.
Telegram custom emoji 100x100: make it from a 1024x1024 image
Telegram custom emoji are exactly 100x100, PNG or WEBP. 100x100 is far below GPT Image 2.5's size floor, so request 1024x1024 on Sume and scale it down.
Telegram sticker size 512: transparent PNG from an image API
A Telegram static sticker needs one side exactly 512 px, PNG or WEBP. On Sume, request a transparent 1024x1024 GPT Image 2.5 PNG, then resize to 512x512.
YouTube channel banner 2560x1440: size, 6 MB cap, API request
YouTube's channelBanners.insert wants 2048x1152 minimum, 2560x1440 recommended, 16:9, max 6 MB. 2560x1440 passes GPT Image 2.5's size rules on Sume.
Amazon A+ comparison carousel images: 488x700 portrait, 600x450
The Premium Comparison Carousel needs 3 to 5 product images of at least 488x700 plus 600x450 mobile images. Sume-legal sizes are 800x1152 and 960x720.
Amazon A+ hotspot image module: make the 1464x600 art first
The Premium Hotspot Image module puts markers on a desktop image of at least 1464x600. Generate it at its final size (1472x608) before placing hotspots.
Amazon A+ video and image carousel: 2 to 6 panels, one trim each
The Premium Video Image Carousel has 2 to 6 panels, each with its own video or image. Cut one product film into per-panel clips with Sume's video trim.
Amazon A+ video text module: an 800x600 preview from your clip
PremiumVideoTextModule needs a video preview image of at least 800x600. Extract that still from your own Sume clip with the unbilled video frames call.
Amazon Brand Story hero image size: 1464x625 desktop, 463x625 mobile
Brand Story's image-with-logo card needs a desktop image of at least 1464x625 and a mobile image of 463x625. Sizes that pass Sume's 16-pixel rule.
Amazon Brand Story card specs: 362x453 image, 166x182 ASIN tile
Brand Story's media asset card needs 362x453 or larger and the four-ASIN card 166x182. Which Sume canvases clear its 16-pixel and pixel-floor rules.
Amazon A+ four-column images: 300x225 minimum, made as 4:3
Amazon's Premium four-column A+ module needs images of at least 300w x 225h. Make them as 4:3 stills at 1024x768, which clears Sume's pixel floor.
Amazon Premium A+ full background image: ask for 1472x608
Amazon needs a desktop image of at least 1464x600, and 1464x600 is not a multiple of 16. Request 1472x608 on openai/gpt-image-2.5 and a 960x720 mobile image.
Amazon Premium A+ hero video: 960x540 video, 1464x600 preview
Amazon's Premium Hero Video module wants a video of at least 960x540 and a preview image of at least 1464x600. Plan a 16:9 clip and a separate still.
Amazon Premium A+ image carousel: six slides, twelve images, a plan
The Premium Image Carousel takes 2 to 6 slides, each with a 1464x600 desktop and 600x450 mobile image. Plan twelve image requests and optional bulk runs.
Amazon A+ regimen carousel: step images for a routine or gift set
The Premium regimen carousel holds 2 to 5 step panels with tabs. Plan one image per step, desktop and mobile, and the Sume Format for usage footage.
TTS per sentence, then concat: join up to 20 clips in one file
Generate TTS one sentence at a time, then join up to 20 clips with Sume timeline audio concat: sample-domain, no re-synthesis, $0.01 flat per job.
Captions app 10-minute captions vs Sume's 60-second inline cap
Captions processes videos up to 10 minutes. Sume's inline avatar captions reject estimates above 60 seconds; standalone video-captions is a separate job.
Captions AI Twin from a video upload vs Sume's photo avatar
Captions can build an AI Twin from an uploaded video. Sume's avatar API takes a prompt, a profile or a public HTTPS reference image, but no video input.
Captions Avatar Looks in Prompt to Video: the Sume handle workflow
Captions saves looks inside one avatar for Prompt to Video. For several looks in Sume, make one avatar_handle per look and render one job per final video.
Captions horizontal 16:9 AI Edit vs Sume avatar aspect ratios
Captions AI Edit now outputs 16:9. Sume avatar videos accept 16:9 too, at 720p only, with a script or plan estimated at 4-60 seconds. 9:16 is the default.
Captions app SRT export vs Sume burned-in caption cues
The Captions app can export an SRT file for external caption tracks. Sume burns captions into the MP4 from authored cues with text, start and end.
EU AI icon alt text and ARIA label for AI-generated video
The Commission says the EU AI icon should, if possible, be readable by assistive technology via alt text or ARIA labels. Burned-in pixels need text in the page.
EU AI icon: black, white or 50% transparency on video?
The EU AI icon has four variations. Pick the one that stays clearly perceivable on your footage; test each on a bright and a dark scene with Timeline compose.
EU AI icon for fully AI-composed music: generated tracks
The EU icons page lists fully AI-composed music or art under the Fully AI-Generated icon, with limited disclosure for artistic works. Handling a Sume track.
Small business holiday ad creative with AI: one Format, one bulk run
Google showed three creatives building local campaigns with Flow. A shop can run a first-party Sume Format per product and queue up to 100 runs in a bulk call.
Overlay a graphic on avatar video: Sume compose overlay step
HeyGen's demo fades a HyperFrames composition over a live avatar. On Sume, put one still over finished avatar footage with timeline compose operation overlay.
Instagram messaging API multiple images: make a set in one call
Instagram's multiple-image messages left beta on May 6, 2026. Generate a four-image set with one Sume images call and send the hosted URLs yourself.
Instagram Edits assistant: cut a 7-second reel with Sume video trim
The Edits assistant told one creator to mix a 7-second reel among 1-minute videos. Cut a 7-second version of a longer reel with video trim, from 0.2 seconds.
Krea 2 style references and moodboards vs Sume reference images
Krea 2 style transfer uses one or many reference images, and moodboards take dozens. Sume takes reference image URLs on input_references, capped per model.
Luma Scenes: approve keyframes, then render, on Sume
Luma Scenes renders only after you approve each keyframe. On Sume, make and approve a still first, then submit it as first_frame so you pay for video once.
Luma uni-1 multi-panel storyboards vs Sume n images
Luma uni-1 can draw a multi-panel storyboard in one image when the prompt describes panels. Sume n returns up to 10 separate images, per-model limits lower.
Luma Variants placements: which ratios a Sume image can hit
Luma Variants outputs 9:16, 4:5, 1:1, 6:5 and 16:9. Sume's image ratio list has four of those five; 6:5 is not in it, so plan a crop for that slot.
Size-by-language ad matrix: one Sume job per cell
Luma Variants returns every size and language pair from one master. On Sume each pair is a job, so 2 sizes and 2 languages is 4 submits against plan capacity.
Mercado Libre Clips with AI: leave off prices and static images
Mercado Libre Clips rejects prices, coupons, static images and third-party music. Burn approved wording with Sume captions and keep stills out of the edit.
Mercado Libre Clips requirements: 9:16, 10-60 seconds, with sound
Mercado Libre Clips needs vertical 9:16, 10 to 60 seconds, and voice or music. One seedance-2.5 call reaches 30 seconds; a full minute needs two clips.
Meta Advantage+ and 3+ formats: one product clip, three shapes
Meta says adding 3 or more creative formats helps Advantage+ match creative to the surface. Conform one product clip to three sizes with video trim output.
MiniMax H3 license: AI-generation identifier is encouraged
MiniMax H3 license III.3.b encourages, not requires, an AI-generation identifier on files. Sume documents a visible plate or burned captions, not metadata.
Pinterest Performance+ Priority Products: build a creative set
Priority Products lets Performance+ favor chosen products for a seasonal launch. Make a 2:3 image set for those few products, not the whole catalog.
Pinterest A/B testing: two Pin creatives from one reference image
Pinterest's self-serve A/B test compares creative or targeting. Change one thing between two Pin images made from the same reference with Sume.
Reuse one winning ad across a catalog: one edit job per SKU
To reuse a proven video ad for many products on Sume, send one edit job per SKU with its own Idempotency-Key, and submit in waves so queue_full never hits.
Runway Ad Localization recipe vs a Sume image edit prompt
Runway localizes an ad image from a targetLanguage code like ja. On Sume, send the ad as a reference image and name the language in the edit prompt.