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
Wan 3.0 auto scene splitting vs explicit scene slots in Sume Timeline
Wan 3.0 advertises auto scene splitting inside one generation. If you want control of each scene, build separate clips and join them with Timeline 1.0.
AI music video: a Lyria 3.5 track as the Timeline spine
Generate a song on the Music Router, then cut generated clips to it on Timeline 1.0. Track length is set in the prompt, not a duration field.
Explainer video from a script: Sonic 3.6 voice and Timeline
Build a narrated explainer by generating the voiceover with the TTS Router on sonic-3.6, then rendering slots on Timeline 1.0 at $0.10 per output minute.
New ad in the style of last quarter's spot: reference video
Use a past brand clip as a reference input on gemini-omni-flash-1.1 so a new product spot keeps the look. Reference-to-video accepts image and video, not audio.
Marketplace listing video from one product photo: first_frame
Turn a single product photo into a short listing video by pinning it as the first frame on seedance-2, then check the catalog fields that gate the request.
Localize one product ad into five languages: voice, captions
Keep the picture, swap the language: a per-language voiceover on sonic-3.6, burned captions with a language hint, and one Timeline render for each market.
Brand character keyframe: GPT Image 2.5 refs, then first_frame
Build an opening frame that keeps your character on model with up to 16 reference images on GPT Image 2.5, then animate it by pinning it as the first frame.
Swap the product in a finished video: Omni Flash edit mode
Edit an existing clip with gemini-omni-flash-1.1 through the Video Router video_url field. The source sets length and shape, so aspect_ratio returns 400.
Cookware sizzle video with native audio: Omni Flash 1.1 cost
A 10-second 9:16 cookware ad with native sizzle audio from gemini-omni-flash-1.1: the request, the limits it enforces, and the arithmetic from the list rate.
Mascot dance ad: Kling motion control, orientation and sound
Drive a still mascot with a motion reference video through Kling 3.0 Motion Control on Sume. Settings that matter: duration, orientation and original sound.
Looping product banner: same photo as first and last frame
Pin one product photo as both first_frame and last_frame on seedance-2 so a short clip ends where it started, then loop it in a hero banner or a story.
Animate a trading or tarot card image: pick the model by aspect ratio
Card art is a tall rectangle. Kling 3 and Omni cannot take 3:4 on Sume; Wan 3.0 and MiniMax H3 can. A 5 second 3:4 card costs $0.3125 on Wan at 480p.
TikTok ad minimum 540x960 vs 480p AI video: which resolution to pick
TikTok's ad spec asks for 9:16 video of at least 540x960. A 480p AI clip falls short on its short side. Generate at 720p or higher on Sume.
Morph one photo into another: first and last frame cost by model
To morph photo A into photo B, send A as first_frame and B as last_frame. Grok cannot; Kling 3, Wan 3.0, H3 and Omni can. 5 s costs $0.31 to $0.70.
Briefing a TikTok ad from trending search: fields and limits
Use POST /v1/trending-videos/search to collect ranked TikTok metadata for a product keyword, then turn the hooks into a brief. Fields, limits, no downloads.
Amazon product video shows about 3 days after approval: plan back
Amazon says shoppable product video typically displays within three days of approval. Work back from a launch date with a small planner and Sume lead times.
Amazon product video shows in the main block only under six images
Per Amazon's seller guide, a shoppable video shows in the main media block only if the listing has fewer than six images. Plan gallery and clip together.
Four shoppable videos per ASIN: demo, how-to, lifestyle, unboxing
Amazon allows up to 4 shoppable videos per ASIN for sellers with a professional account and three months of history. A four-clip plan batched on Sume.
Amazon allows four shoppable videos per ASIN: eligibility and plan
Amazon allows up to four shoppable videos per ASIN for professional sellers with three months of history. A demo, how-to, lifestyle and unboxing plan.
Amazon Sponsored Brands video: 1 Mbps and 96 kbps audio minimums
Amazon Sponsored Brands video needs at least 1 Mbps video, 96 kbps audio at 44.1 kHz, and 16:9 only. What to check on an AI-generated clip before upload.
Demand Gen logo 150 KB, images 5 MB: check sizes before upload
Demand Gen allows images up to 5 MB but logos only 150 KB. Check bytes on every Sume image before upload, since output compression is not served in v1.
Demand Gen carousels: 2 to 10 matching cards from one reference
Demand Gen carousels take 2 to 10 cards. Image assets run 4:5 or 9:16 at 5 MB. How to batch matching cards from one reference image with the Sume image API.
Performance Max image assets: three ratios, 5120 KB cap, 20 each
Performance Max wants landscape 1.91:1, square and 4:5 portrait images up to 5120 KB, 1 to 20 each. How to batch a matrix of images on Sume. Read 2026-10-03.
Performance Max logo assets: 1200x1200 square and 1200x300 landscape
Performance Max takes a 1:1 logo at 1200x1200 (minimum 128x128) and a 4:1 landscape logo at 1200x300. How to prepare both with Sume. Read 2026-10-03.
Shopify video storage by plan: 50 GB, 500 GB, 2 TB, and a clip cap
Shopify caps video and 3D files by count (250 to 100,000) and storage (50 GB to 2 TB) per plan. A short script finds which limit your AI clip batch hits first.
Article 50(2) assistive editing: trim and crop vs generate
Article 50(2) exempts assistive editing that does not substantially alter input. Sort your Sume outputs into generated and file-processed before you rely on it.
Article 50: creator duties vs provider duties, side by side
Article 50(4) puts deepfake and certain text disclosure on deployers, while 50(2) puts marking on providers. A two-column split for teams that publish AI video.
EU AI Act Article 50 timeline: code of 10 June, duties from 2 August
Article 50 transparency duties apply from 2 August 2026. The final labelling code was published 10 June 2026, with about 190 signatories by end of July.
Article 50(2): the provider duty to mark AI outputs machine-readably
Article 50(2) makes providers mark synthetic outputs in machine-readable form. What the wording says, what is exempt, and what to ask a generator vendor.
Snap ad video size: API says 1080x1920, ad specs page says 720x1280
Snap's Ads API lists 1080x1920 for top snap video while its ad specs page lists 720x1280. Render one 9:16 file at 1080p and check the pixels with Sume.
Snap image ads become 5-second videos: generate a real clip instead
Snap's Ads API converts a top snap image into a 5-second video. If you want camera motion, generate a 5-second clip from the same image with Sume.
Snapchat ad specs: 9:16 only, 3 to 180 s, a simple batch target
Snap's ad formats page lists 9:16 at 720x1280 and 3 to 180 s for most formats. The Ads API page says 1080x1920. How to render one file that fits both.
Reels ads: 9:16, sound on, and a safe-zone brief for generated clips
Meta says Reels default to sound on and favours 9:16 video with audio and key messages in the safe zone. A brief for generating clips that follow it.
Meta ad video length by placement: 15 s to 240 min
Meta's placement chart sets different lengths and ratios per placement, from 15 s Messenger Stories to 240 min Feed. A render plan by placement.
One 9:16 master for Instagram ads: what two Meta pages say
Meta's Instagram Feed video ad page lists 9:16 at 1080x1920 and 4 GB. Its placement chart shows a narrower Feed range. How to pick a master and check it.
Meta auto-detects AI-made ads: plan for the AI info label
Meta says its ad system detects ads made or edited with third-party AI tools through industry-standard signals and may show an AI info label. What to prepare.
Meta labels AI images from C2PA and IPTC metadata: what stripping does
Meta reads C2PA and IPTC invisible metadata to label AI images. What the February 2024 post says, what it leaves open for video, and how to check files.
YouTube AI label: player or description, by how real it looks
YouTube shows the altered or synthetic label in the player for photorealistic content, in the expanded description for animated. What it means.
Shopify product video: five recommended ratios at 30 to 60 fps
Shopify recommends 16:9, 9:16, 4:3, 3:4 or 1:1 video at 30 to 60 fps. Seedance 2 on Sume lists the same five ratios, so one prompt can fill a full ratio set.
YouTube end screens need a 25-second video: plan the clip length
YouTube end screens need videos 25 seconds or longer. Most Sume video models stop at 15 seconds, so here is how to reach 25 with long models or Timeline.
Meta AI disclosure: which Sume outputs count, video and audio
Meta asks for disclosure of photorealistic video and realistic audio that was digitally created or altered. A sorting guide for video, avatar and music.
Pinterest ad disclosure: "modified with AI" or "AI-generated person"
Pinterest labels AI content from IPTC metadata, classifiers and creator disclosure. For ads you disclose via the ellipsis menu. Which wording fits which image.
Kling 4.0 lip-sync reaches nine languages: a one-clip test each
Kling 4.0 adds Portuguese, German, French and Hindi lip-sync to five existing languages. A short per-language test plan to run before you promise localization.
Seedance 2.5 C2PA, watermark and real-face rules: an ad checklist
BytePlus lists C2PA credentials, visible watermarks and real-face limits for Seedance 2.5. A checklist of what to confirm and record before an ad clip ships.
Pinterest see-fewer AI Pins: beauty, decor, fashion, food and drink
Pinterest's see-fewer GenAI controls cover beauty, art, fashion, decor, health and sport, plus food and drink from December 12, 2025. What it means for Pins.
Kling 4.0 keyframes at 0, 6, 12, 20, 28 s: a 30-second ad on Sume
Kling's guide suggests keyframes near 0, 6, 12, 20 and 28 seconds for a product ad. How to build the same plan on Sume with first-and-last-frame clips.
TikTok Shop LIVE: stills may cover only half the screen
TikTok Shop seller guidance caps stills and slideshows at 50% of the screen during a LIVE. Plan overlay layouts with motion clips from Sume instead of stills.
TikTok Shop main image: no digital renderings, and the real-model shot
TikTok Shop's listing guidance excludes digital renderings from the main image and asks for a real human model image. What that means for AI product shots.