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
Blend two videos together API: what Sume can and cannot layer
Sume cannot blend two videos into one frame: video filter works on one clip, and compose puts one still over one video. Two videos join in sequence on Timeline.
Keep one color, rest gray, in a video by API with colorhold
Use colorhold in Sume's video filter to keep one color and gray out the rest of a clip. Free check first, then one encode job on sources up to 300 seconds.
Copyright Office Part 2: prompts alone, and arranging AI video
The US Copyright Office says prompts alone give too little control, but selection, arrangement and modification can count. Which Sume edits arrange.
Fix flicker in AI video with the deflicker filter API
Brightness flicker between frames can be smoothed with the deflicker filter in Sume's video filter. It will not fix shimmering detail. Check free, then encode.
Draw a box on a video with the drawbox filter API
Burn a review box onto a clip with the drawbox filter in Sume's video filter. drawtext is not allowed, so labels need captions. Check first, free.
ElevenLabs Music Finetunes vs a reusable Sume Music brief
ElevenLabs Finetunes train on your own tracks in about 5-10 minutes. Sume Music 1.0 has no training step; keep a brand sound with a reusable prompt brief.
AI Act standard-editing exemption: trim, filter, caption steps
The Commission FAQ exempts AI assisting standard editing from marking. Which plain edit steps Sume exposes (trim, dim, crop, caption), and what to check.
AI Act deepfake disclosure at first exposure: marking is not enough
Per the Commission FAQ, deployers disclose a deepfake at first exposure in a form people can perceive; the provider's machine-readable mark alone is not enough.
AI Act deepfake definition: the three cumulative criteria
A deepfake under the AI Act needs three cumulative criteria per the Commission FAQ: resemblance, an existing subject, and a false appearance of authenticity.
AI Act artistic or satirical deepfakes: a lighter disclosure
For evidently artistic, satirical or fictional works the Commission says disclose in an appropriate manner that does not hamper enjoyment. Credit or banner?
EU AI icon with a "voices generated with" label on avatar video
The Commission's example pairs the basic EU icon with the text "voices generated with". Here is how to author that line as caption cues on a Sume avatar video.
Faceless education video episodes, 1-5 minutes, on Sume Timeline
Build a 1-5 minute faceless education episode on Sume: one narration track plus scene stills on a Timeline 1.0 document you reuse for each new episode.
Fix color banding in AI video: the deband filter API
Visible steps in skies and gradients can be softened with the deband filter in Sume's video filter, with noise as a fallback. It returns a new MP4. Check free.
Fix washed-out, flat video: normalize or histeq filter API
Flat, washed-out footage can be auto-leveled with the normalize or histeq filter in Sume's video filter, or tuned by hand with colorlevels. Check it free first.
FLUX.2 interior design edit: repaint walls, swap flooring
Send a room photo as a public HTTPS image URL plus a prompt naming the change. BFL describes the FLUX.2 use case; Sume takes it as a reference edit.
FLUX infographic prompts: layout, icons, palette, one Sume request
BFL says to specify layout, content hierarchy, icons and color palette in a FLUX infographic prompt. Here is that prompt sent as one Sume image request.
FLUX UI mockup prompts: app screens and game UI via one API call
Describe layout, sections and visual style in the prompt, pick a portrait or landscape aspect_ratio, and use n to get several concepts in one Sume call.
AI frame interpolation API: 24 to 60 fps on Sume
Sume has no AI interpolation model. Timeline repeats or drops frames to reach 60 fps, video filter allows an ffmpeg framerate filter, and setpts is refused.
Gemini Media Watermark setting: visible off, SynthID stays
Gemini Apps' Media Watermark setting turns off only the visible mark. SynthID and Content Credentials stay on. India, South Korea and Vietnam need AI Ultra.
Hue shift a video's colors by API for a Candy Pink look
Shift a whole video's hue and saturation with the hue, vibrance and colorize filters on Sume's video filter. One encode job, one new MP4, no preset library.
Ideogram Sketch to Render API vs a Sume image reference edit
Ideogram's Sketch to Render turns a fashion sketch into garment imagery. On Sume, send the sketch URL in image_urls with a prompt describing materials.
Invert video colors by API with the negate filter
Send filtergraph negate to Sume's video filter to invert a clip's colors. A typo in the filter name is refused with invalid_filtergraph before any encode.
Add black frames to the start or end of a video with tpad
Use the tpad filter on Sume's video filter to add black frames before or after a clip. A few lines of graph, one encode job, a new MP4 with handles.
ProRes 4444 or PNG sequence from AI video: Sume returns MP4
Sume's video jobs return an MP4, not ProRes 4444 or a PNG sequence. Frame stills at times you name come from video frames as images. What to use instead.
Relight a video with AI by API: pixel filters or a prompted edit
Sume has no relight preset. Darken or lift tone with the dim op and exposure or eq filters, or describe new lighting in a video edit prompt. What each can do.
Seedance real-face reference images rejected: what to do
BytePlus says Seedance 2.5 and 2.0 do not accept reference images or videos with real human faces. The exceptions, and a safe reference plan on Sume.
Sepia or blue tint filter for video by API
Tint a clip sepia or blue with colorchannelmixer, colorbalance or monochrome in Sume's video filter. Presets and .cube LUT files are not available.
Sharpen video after an upscale: unsharp or cas filter API
Sharpen an upscaled clip with the unsharp or cas filter in Sume's video filter: one MP4 in, one new MP4 out, a flat per-job rate, and a free check first.
Split screen from one video by API: split and hstack
Put a clip beside its own filtered copy with split and hstack in Sume's video filter. One source in, one side-by-side MP4 out. Video filter takes only one clip.
Spotify AI credits in Song Credits: DDEX disclosure for AI music
Spotify shows AI credits in Song Credits only when your label or distributor submits the DDEX disclosure. No credit does not mean no AI. Keep job notes.
Stop-motion look at 12 fps: use the video filter fps filter
Timeline output.fps stops at 24, 25, 30 or 60. To get a choppy 12 fps look, run the fps filter in Sume's video filter and get a new MP4 for $0.02.
Sync dubbing in 92 languages vs building a dub on Sume
Sync's built-in dubbing now lists 92 languages with speaker detection. Sume has no dubbing endpoint: chain transcription with a language hint, translation, TTS.
TikTok invisible watermark on reupload: what it covers
TikTok is testing invisible watermarks on AI Editor Pro content and on uploads with C2PA Content Credentials, since labels can vanish on reupload or edit.
Fix tilted video perspective by API with the perspective filter
Sume's video filter allowlists ffmpeg's perspective filter, so you can pull a keystoned phone clip back to a rectangle. You choose the four corner points.
Tumblr video pixelated? Upload 720p H.264 MP4, not a 360p source
Tumblr re-compresses every upload and aims for 720p H.264 MP4. Ask for 720p when you generate, avoid 360p, and trim with exact mode to limit extra passes.
Tumblr video limits: 20 a day, 10 minutes each, 60 minutes, 500 MB
Tumblr allows 20 videos a day, 10 minutes and 500 MB per video, 60 minutes in total. How to size AI video batches, trims and clip lengths to fit.
YouTube AI label: below the player, and an overlay on Shorts
Since May 2026 YouTube shows one AI label below the player on long-form and as an overlay on Shorts. What a burned-in caption line adds, and what it does not.
YouTube AI label can't be removed: Veo and C2PA cases
YouTube keeps the AI disclosure permanent for its own AI tools such as Veo, and for files whose C2PA metadata says fully generative. What that means.
YouTube added an AI label to my video: how to change it
From May 2026 YouTube may label a video itself when it detects photorealistic AI. If it is wrong, update the disclosure in YouTube Studio; re-editing will not.
AI background music for a video: Lyria 3.5 plus Timeline soundtrack
Google lists background music as a Lyria 3.5 template. Generate a bed with Sume's Music Router, then lay it under narration with Timeline soundtrack ducking.
AI birthday song generator by API: Lyria 3.5 on Sume
Google lists custom birthday tracks as a Lyria 3.5 template. Here is how to generate a birthday song with the Sume Music Router and what it costs.
AI brand jingle generator by API with Lyria 3.5 on Sume
Google lists brand jingles as a Lyria 3.5 template. How to brief a short jingle with the Sume Music Router, keep it instrumental or sung, and cost it.
AI ringtone maker by API: Lyria 3.5 plus a Timeline audio cut
Google lists personalised ringtones as a Lyria 3.5 template. Generate the track with Sume, then cut a short wav or mp3 clip with Timeline audio split.
Apple Podcasts video uses HLS: what Sume renders instead
Apple Podcasts video is delivered by HLS through hosting providers. Sume renders an MP4 episode with Timeline; it does not produce HLS.
Chrome Web Store 440x280 promo tile: generate at 1760x1120
The Chrome Web Store small promo tile is 440x280, below GPT Image 2.5's pixel floor. Request 1760x1120 (exact 4x, same 11:7 ratio) on Sume and downscale.
Chrome Web Store screenshots at 1280x800: request it directly
Chrome Web Store screenshots are 1280x800 (or 640x400), JPG or PNG, square corners, full bleed. 1280x800 passes GPT Image 2.5 rules, so request it on Sume.
Cost per SKU for an AI product video: 500 holiday SKUs priced
What one vertical product clip costs on seedance-2.5 at 480p and 720p for 6 and 10 seconds, and what 500 SKUs add up to. Computed from Sume's pricing code.
Cost to transcribe 1,000 hours of audio with an API
1,000 hours is 60,000 minutes: $600 at Sume's $0.01 per minute, in 6,000 or more 10-minute jobs. OpenAI's listed transcription rates give $270 to $1,020.