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
AI cross-stitch pattern: generate art, then grid and count in Pillow
Turn an AI image into a cross-stitch chart: generate simple art, shrink it to a stitch grid, cut to N colours and count stitches per colour with Pillow code.
AI memory match game cards: 8 pairs, one style, deck built in code
Make a memory-match deck with the image API: eight subjects in one style via a reference image, then duplicate, shuffle and lay out the deck in Pillow.
AI postcard via API: 3:2 front art, address side drawn in code
Make a postcard front at 3:2 with GPT Image 2.5 custom pixels, then draw the back with message, address lines and a stamp box in Pillow. Code runs as written.
AI shopping referrals up 693%: a Sume output schema for listing copy
Adobe data in KTVZ has AI referrals to US retail up 693.4% in Nov-Dec 2025. Bind a headline, hero image and alt-text schema so each video returns typed JSON.
Bandcamp bans AI music: can a video bed be substantially AI?
Bandcamp bars music made wholly or in substantial part by AI. Where a video soundtrack made with Sume's Music Router sits, and how to keep a human lead.
Christmas ad music: an instrumental Lyria brief that sells
A Christmas ad needs music that is festive without vocals under the voiceover. Brief it in one prompt, set the bed under speech and fade it out, with Sume.
Cyber Week five-day creative sprint: a daily Seedance clip budget
Shopify defines BFCM as Thanksgiving through Cyber Monday. Twenty-two 8-second 720p vertical clips across those five days cost $101.6928 on Sume.
E-commerce product video cost per SKU: cutout plus a 5-second clip
A cutout at $0.0225 plus a 5-second 720p Seedance 2.5 clip is $2.9115 per SKU on Sume. For 100 SKUs that is $291.15. Arithmetic inside.
Game trailer score: section markers for a Lyria 3 Pro brief
Score a game trailer by marking sections in the prompt, pinning lyria-3-pro on Sume's router and cutting picture to the result on a Timeline render.
Halloween video sound design: a Lyria prompt that stays scary
Halloween trailer and ad sound design with one prompt to Sume's Music Router: drones, stingers and a quiet bed, no vocals, plus a silent-clip caption fallback.
Holiday ad voiceover and music bed: cost per spot, 300-900 chars
On Sume a 600-character voiceover costs $0.0285 and a music track $0.125 flat, so a spot with both is $0.1535, before the video.
IFPI AI chart rules: scoring a music video with AI audio
IFPI's July 30, 2026 chart principles ask for lawful AI services and substantially human-made tracks. What that means for a music video score on Sume.
In-store screen loop: a 30-second 16:9 clip at 720p vs 1080p on Sume
A 30 s 16:9 Seedance 2.5 clip costs $17.334 at 720p and $42.6465 at 1080p on Sume. Wan 3.0: $3.75 and $7.50.
Lofi study stream: a 30-second track looped as a Sume soundtrack
A lo-fi study stream needs a bed that repeats cleanly. Generate a 30-second track with Sume's router and loop it under a video with soundtrack.loop.
Mixed-language explainer: two TTS jobs joined into one track
A voice that handles 23 or 90 languages still needs one language per request. Render each language as its own job, then join the takes with timeline audio.
Re-render only the SKUs that changed: hash rows for a Sume bulk run
Retail surveys cite inventory imbalance and reactive decisions. Hash each product row, then send only changed rows to a Sume bulk queue with a revision key.
Spotify's AI Persona badge: labeling an AI music video channel
Spotify will badge AI Persona profiles and skip them in recommendations. What a video channel with generated audio should label and keep.
Autoplay avatar welcome video with sound: WCAG 1.4.2 rule
Can an AI avatar welcome video autoplay with sound? WCAG 1.4.2 allows it only with a pause or volume control once audio runs past 3 seconds.
Wedding highlight video music: an original score, not a pop song
A wedding highlight film needs music that fits its length. Generate an original instrumental with Sume's Music Router and place it under the clips.
YouTube Dream Track for Shorts: a Lyria soundtrack through an API
Dream Track makes 30-second Lyria soundtracks inside YouTube Shorts. If you need that outside the app, Sume's Music Router returns a file for any video.
Vietnam AI Law Article 11: labelling real people, real events
Under Vietnam's AI Law, deployers must label AI media that imitates a real person's face or voice or recreates a real event. Art and film get a softer rule.
IPTC compositeSynthetic vs compositeWithTrainedAlgorithmicMedia
Both IPTC terms mean a composite with generative AI in it. One says edited using generative AI; the other says a composite where at least one element is Gen AI.
IPTC minorHumanEdits was retired: use humanEdits instead
IPTC retired minorHumanEdits on 2024-09-17 and replaced it with humanEdits. Which Sume edits (trim, filter, caption) are non-generative ffmpeg passes.
YouTube 9:16 on desktop: white padding, and don't bake bars in
YouTube adds white padding (dark gray in Dark theme) around 9:16 video on computers, and says not to add bars yourself. Match the shape in Timeline.
CAWG training and data mining 1.1: notAllowed vs constrained
The CAWG training-and-data-mining assertion has four entries, each allowed, notAllowed or constrained. Constrained with no extra info counts as notAllowed.
Vietnam AI Law Article 11: machine-readable marks for AI media
Vietnam's Law No. 134/2025/QH15, in force 1 March 2026, makes AI providers mark audio, image and video in machine-readable form. Sume docs show no such mark.
CAWG identity assertion 1.2: who made it, not whether it is AI
A CAWG identity assertion says which named actor stands behind an asset. It does not say the asset is AI-generated. What Sume stores that you can pair with it.
LinkedIn Life tab images: 1128x376 main, 900x600 photos
LinkedIn Life tab sizes: main image 1128x376, custom modules 502x282, company photos 900x600 recommended. Request each from Sume at a legal size, then fit.
LinkedIn Page cover 1512x256 and logo 400x400, 3 MB cap
LinkedIn Page covers are 1512x256 and logos 400x400 recommended, PNG or JPEG under 3MB. Crop a Sume 1536x512 image to 1512x256 with the exact box.
LinkedIn newsletter logo 300x300 and cover 1920x1080
LinkedIn recommends a 300x300 newsletter logo and a 1920x1080 cover per article. 1080 is not a multiple of 16, so ask Sume for 1920x1088 and trim 4 px.
LinkedIn profile photo 8 MB, 400-7680 px, plus 1584x396 banner
LinkedIn takes a PNG or JPG profile photo up to 8 MB and 400x400 to 7680x4320 px; the background is 1584x396. How to reach 4:1 from a Sume 3:1 image.
LinkedIn Page link post image: 1200x627, over 200 px wide
For a LinkedIn Page post with a URL, use a 1.91:1 image at 1200x627 and more than 200 px wide, or it shows as a left thumbnail. Request 1280x672 from Sume.
Dribbble shot image: 1600 px wide, 10 MB, PNG JPG or GIF
Dribbble recommends images at least 1600 px wide and takes PNG, JPG or GIF up to 10MB. Sizes Sume can generate at 1600 wide, and a script to check the file.
Dribbble shot video: 20 MB limit and the bitrate budget
Dribbble allows MOV or MP4 video up to 20MB and recommends 1600 px width. What 20MB means in average Mbps by clip length, and which Sume Timeline fields help.
Holiday clip for a marketplace video slot: what to check before upload
Amazon, Shopify, Etsy and TikTok Shop each set their own video rules. Sume gives you ratio, length and size controls; read each platform's current page.
Estate sale preview video from mixed portrait and landscape photos
Phone photos of estate sale lots come in both orientations. Timeline's fit modes (cover, contain, stretch, blur) decide whether a lot is cropped or kept whole.
Rehearsal dinner slideshow: 24 photos and Timeline's 8-fade cap
A 24-photo slideshow with fades fails if every cut is a fade: Timeline refuses more than 8 chained transitions. Insert hard cuts; 96 seconds costs $0.20.
Classroom projector lesson video in 4:3: set the avatar aspect ratio
Avatar Video defaults to 9:16, so a lesson for an older 4:3 projector needs aspect_ratio set to 4:3. Five ratios are supported; resolution is 720p.
Tutor intro video: approve the first frame, then pick the tier
A tutor can approve an avatar intro's first frame before paying for the full render, then choose standard, plus or max at generate-video without a new preview.
Home renovation before and after video: start and end frame
Make a renovation reveal clip from two photos: send the before as image_url and the after as end_image_url to Gemini Omni Flash 1.1, 3 to 10 seconds.
Anniversary video from old photos: three 10-second clips and a song
Animate three old photos with Gemini Omni image_to_video, 10 seconds each, then join them over a Lyria 3.5 track in Timeline. 30 seconds bills at $0.10.
Planned maintenance notice video: preview the frame, then render
Send a 20-second planned-maintenance video with a Sume avatar: create a preview, check the frame, then call generate-video once. Cost by tier included.
Black Friday ad fatigue: refresh a clip with a new first second
When a Black Friday ad stops converting, keep the footage and change the opening: a new hook, new caption cues and a new music bed, for about $0.30 per refresh.
AI character sheet with turnaround and expressions via API
Build a character sheet with front, side, back and expression views: pick one anchor image, then feed it back as a reference per view on gpt-image-2.5.
Graduation announcement video: first frame, then names as caption cues
Start a graduation clip from a cap-and-gown photo as first_frame on /v1/videos, then put the names and date on as caption cues instead of generated text.
Weekly toolbox talk as a 45-second avatar clip: 52 weeks priced
A weekly 45-second safety briefing from a Sume avatar on a worksite photo, captions on: 52 clips cost $440.96 on Standard. Tiers and script rules.
AI baby announcement card via API: art from the model, name from code
Make a baby announcement card: generate illustrated art at 3:4, crop to 5x7, and set the name, date and weight in code. Plus a privacy check on photo URLs.
Test six Black Friday openers on Wan, then finish one on Seedance
Draft six Black Friday hooks as 5-second Wan 3.0 480p clips for $1.875, pick one, and finish it on Seedance 2.5 720p for $4.62. Total $6.70 with captions.