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
Royalty-free AI music for TikTok ads: what the phrase does not settle
Royalty-free does not mean licensed for ads or cleared for a platform. What to check for AI music before a TikTok ad, using reported facts and a record to keep.
Runway Enhance Frame Rate on a Sume clip: get the MP4 first
Runway says Enhance Frame Rate works on any video, not only Runway-made. To run it on a Sume clip, download the finished job's MP4 from its content URL.
Suno lawsuits still pending: a risk checklist for ad music
Suno v6 is trained on licensed data, yet TechCrunch reports suits from Sony, UMG and artists continue. A checklist for using any AI music in an ad.
A 10-minute avatar module on Sume: ten jobs, priced by tier
Sume avatar videos run 4 to 60 seconds, so a 10-minute module is ten jobs and a join. Standard comes to $110.40 and plus to $147.00, by arithmetic from list.
Text edited in an ad image: a dimension check before you ship
After an AI text replacement, compare output and source dimensions in Pillow. Stretched or recropped edits are caught in one assert, before the ad goes live.
TikTok's reported 24 hours to disclose or appeal, and a burned-in fix
A brand-agency summary reports TikTok gives 24 hours to add a disclosure or appeal. A plan for that day, and a Sume captions call that burns the line in.
TikTok 90-day violation window: a label ledger for AI batches
If a summary's 90-day violation window is right, one unlabeled batch can cost a posting ban. Build a per-clip ledger from Sume job ids before you post.
TikTok bans AI-generated endorsements: avatar demo or testimonial?
A brand-agency summary reports TikTok prohibits AI-generated endorsements. How to tell an avatar product demo from a testimonial before you write the script.
TikTok AI label penalties: the four tiers one summary reports
A third-party summary lists four TikTok penalty tiers for unlabeled AI content, from a warning to a ban. What it says, what it leaves out, and what to log.
AI thumbnail or real frame for TikTok? The label angle, and a pick
A snippet reports AI-assisted thumbnails need no TikTok label. Pick a real cover frame with Sume video frames, or generate one and treat it as AI content.
TikTok joins the C2PA steering committee: what to log per AI clip
TikTok is reported to have joined the C2PA Steering Committee in July 2026. What that suggests about provenance checks, and the record to keep for each clip.
TikTok's reported detection methods and what to check in your clip
A summary reports TikTok flags AI via C2PA metadata, visual artifacts and audio fingerprinting. What you can check first with Sume inspect and audio detach.
TikTok impersonation deepfake ban: use face swap with your own avatar
A summary reports TikTok prohibits impersonation deepfakes. Sume's Face Swap (Beta) puts a ready avatar into a video. How to use it without impersonating.
AI background behind real product footage: TikTok's reported rule
Audit Socials reports TikTok wants a label on photorealistic AI backgrounds. When real product footage sits on a generated scene, and what to record with Sume.
Real-person deepfake on TikTok: the reported 30-day tier and avatars
A summary reports a 30-day TikTok suspension for real-person deepfakes. What that means when an avatar starts from a photo, and what to keep on file.
Preflight an AI UGC ad for TikTok: is the disclosure on screen?
Undisclosed commercial content can be reach-limited, one summary reports. Use Sume video frames and inspect to confirm the burned-in line before you upload.
Unlabeled AI video flagged after posting: what to do on TikTok
A summary reports unlabeled AI content flagged later may get a temporary distribution hold. A recovery plan and what Sume can and cannot fix after posting.
Upscale a 5-minute clip on Sume: 30-second parts, then join
Sume Video Upscale takes up to 30 seconds per job. A 5-minute clip is ten parts: trim, upscale each at $0.009 per second, join. The math comes to about $3.41.
Verify a spoken ad disclosure is in the final mix with STT word times
Detach the final ad's audio, transcribe it with Sume STT, and confirm the required line is spoken and when it starts. Python check, not legal advice.
Voice replication blocked in IL, TX, EEA, UK, CH, IN: plan voiceovers
Digital Applied reports Gemini voice replication is unavailable in Illinois, Texas, the EEA, UK, Switzerland and India. A market plan using ready-made voices.
Chain Wan 3.0 clips: last frame of one is the first frame of the next
Extend a Wan 3.0 scene past one clip by extracting a still near the end with video-frames and passing it as the first frame of the next request.
YouTube automatic branded-content labels: a checklist for AI clips
air.io reports YouTube began automatic branded content labeling in September 2026. Keep sponsor facts straight and scan a clip for brand mentions.
YouTube likeness detection now covers voice: what Sume's API does
air.io says YouTube extended likeness detection to speaking voice in August 2026. Sume's API does not clone voices, so what to log and avoid.
Firefly Generate Music for a video vs Sume music with inspect
Adobe Firefly can score an uploaded video. Sume music takes text and an optional image, so inspect the clip first, then write the brief and pass a still.
AI game trailer generator: 4-30 s shots joined in Timeline
Build a game trailer from separate seedance-2.5 shots of 4 to 30 seconds, then join them in Timeline 1.0 with fade or wipe transitions between slots.
Multilingual video captions: language is a hint, not a font
On Sume video captions, `language` only tells speech-to-text what to expect. Look and font come from `style`, `design` and `font`, never from the language.
ElevenLabs agent hold audio: 180 s, 40 MB; make it with Sume
ElevenLabs agent hold audio must be MP3 or WAV, up to 40 MB and 180 seconds. Steer a Sume track's length in the prompt, trim with Timeline audio, export mp3.
FLUX Virtual Try-On v2: 4 MP inputs and a Sume reference edit
BFL's vto-v2 keeps inputs up to 4 MP as-is. Sume has no try-on endpoint in these docs; a garment swap is a reference edit with public HTTPS images.
Seamless looping food video with AI: same first and last frame
To loop a food clip, send one image as image_url and end_image_url to Gemini Omni Flash 1.1, which Google says suits seamless loops. Clips run 3 to 10 seconds.
Gemini TTS two-speaker limit: three-voice dialogue with Sume concat
Gemini TTS configures two speakers per request. For three voices on Sume, make one TTS job per voice and join up to 20 parts with Timeline audio concat.
HeyGen avatar new outfit with reference images vs Sume
HeyGen prompt avatars take avatar_id plus up to three reference_images for a new outfit. Sume's photo input takes one image_url per avatar.
Ken Burns effect API: Timeline stills are static holds
Sume Timeline holds a still image static; motion is accepted and ignored with a motion_ignored warning. zoompan is on the video filter allowlist.
AI kids story video generator: scenes of 2 to 30 seconds
Make a children's story video as one scene per request: wan-3.0 takes 2 to 30 seconds per scene, then join up to 200 slots in a Timeline 1.0 render.
AI real estate walkthrough from photos: chain first/last-frame clips
Kling 4.0 takes up to 10 keyframes for a walkthrough. Sume takes a first and last frame per clip, so chain one clip per room pair and join them on a timeline.
LinkedIn ad image size and AI-generated images in Campaign Manager
LinkedIn single image ads accept JPG, PNG or GIF up to 5 MB, and Campaign Manager has its own AI image tool. Which format to set on a Sume upload.
LinkedIn carousel ad specs: 2 to 10 cards, images only
LinkedIn carousel ads take 2 to 10 image cards up to 10 MB each, 1080x1080 recommended, no video. How to plan the cards with Sume's four-images-per-job limit.
LinkedIn in-stream video ads: up to 90 seconds, in testing
LinkedIn's video ad page says in-stream ads can run up to 90 seconds and are in testing. How to trim a clip to length and make a horizontal and vertical pair.
LinkedIn 4:5 ad image: 720x900, mobile only, no side borders
LinkedIn's vertical single image ad is 4:5 at 720x900 and serves on mobile only; 1:1.91 vertical images get side borders. How to request 4:5 on Sume.
LinkedIn video ad thumbnail and captions: JPG/PNG 2 MB, SRT
LinkedIn wants a JPG or PNG thumbnail up to 2 MB and text-only SRT captions. Sume extracts the frame still; its caption route burns text into the video.
Add a lower third name tag to a video with an API
Sume has no lower-third template. Burn a name and title as one authored caption cue with a newline, and set its height with design.placement.anchor_ratio.
Midjourney style reference API: input_references on Sume
Midjourney's srefs live in its own app. On Sume, carry a style with a public HTTPS reference image in input_references plus a prompt, on models that allow it.
Export one video as 9:16, 1:1 and 16:9 with the API
Call Timeline 1.0 three times with the same clip and a different output.width and height each time. Three renders cost $0.30 for a clip under a minute.
Pinterest ad image size: 2:3, 1000x1500, 40-character title
Pinterest ad images: PNG or JPEG, 2:3 (1000x1500), 100-character title with about 40 showing. Why 1000x1500 clashes with Sume's x16 pixels rule.
Pinterest Collections ads specs: one hero, up to 24 secondaries
A Pinterest Collections ad shows one hero and three secondaries, then up to 24 secondaries fullscreen. No GIFs, desktop only. A batching plan for the assets.
Pinterest white-background Pins get a 4% overlay: what to do
Pinterest puts a faint #000000 layer at 4% opacity on white-background image Pins in light mode. Choose your generated background tone on purpose.
Pinterest Showcase ads specs: title Pin plus four cards
A Pinterest Showcase ad is one 2:3 title Pin plus up to four static cards, with up to three features per card. Plan it as one generated image set.
Pinterest video pin minimum length: 4 seconds, and which models fit
Pinterest's product specs set a 4-second minimum for video pins. seedance-2.5 starts at 4 seconds in Sume; wan-3.0 and Gemini Omni Flash can go shorter.
Podcast video clip in vertical format: 1080x1920 by default
Timeline 1.0 renders 1080x1920 MP4 by default, so a podcast clip is vertical unless you set output width and height. Cut, segment and render steps.