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 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.
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.
AI wall art canvas: gpt-image-2.5 pixels per inch, 8x10 to 24x36
The biggest 2:3 image gpt-image-2.5 can send is 2336x3504, which is 97 pixels per inch at 24x36. Here is the dpi for five canvas sizes and when to upscale.
Vacation rental check-in video: an avatar host with silence beats
One avatar, one shared background and silence beats let a host walk guests through check-in in 60 seconds or less. Set video_inputs on Avatar Video.
Case study video narrated by an avatar: three scenes, 55 seconds
Narrate a written case study as a 55-second, three-scene Sume avatar video: problem, change, result. Cost by tier and a body you can send; no names needed.
AI background music for a one-minute video: brief and cost
Generate a one-minute bed with the Music Router at $0.125 and render it under the video at $0.10 per output minute: about $0.225 in total.
AI board game tokens: transparent PNG art, circle-cropped at 300 dpi
Make board game character tokens: one anchor style, a transparent PNG per character from gpt-image-2.5, then crop to a circle in Pillow at token size.
AI wine label design via API: artwork from the model, text from code
For a wine label, generate only the artwork with gpt-image-2.5, ask for a clear panel, and set the name, vintage and regulatory lines in code so they are exact.
Explainer music that changes per scene: three Lyria briefs, one concat
Make each scene's music a separate Lyria 3.5 brief at least 12 BPM apart, then join them gaplessly with Timeline audio concat for $0.01.
Wedding toast transcript: video inspect with sentence segments
Get a text keepsake of a toast video: video-inspect with transcribe true returns text, word timings and sentence segments for $0.01 per audio minute.
Podcast guest clips from a video call: detach once, then split
Five audio clips from one recorded call cost $0.02 on Sume: one audio-detach ($0.01) plus one timeline-audio split ($0.01), not $0.05 for five detaches.
Out-of-office video message with an AI avatar: 15 seconds on Sume
Make a 15-second out-of-office video from a script: return date, contact, captions on. $2.76 on Standard plus a $0.20 caption add-on; Plus and Max too.
Price increase announcement video: a 45-second avatar, four scenes
Announce a price change with a 45-second Sume avatar video in four scenes: hook, reason, what changes, next step. Cost by tier, a working video_inputs body.
AI cake design preview for a bakery order: photo reference and mask
Show a customer their cake before baking: pass a photo of the plain cake as a reference, edit the top with mask_url, and keep the order text in code.
Hotel guest welcome video: an avatar in your lobby photo, 8 properties
Make a 25-second welcome video per property with a Sume avatar and a lobby photo as the scene: eight properties cost $36.80 on Standard. Script and request.
AI low-poly and voxel icons: a transparent set with one style anchor
Generate low-poly or voxel icons as transparent PNGs with gpt-image-2.5: one anchor icon, then the rest as references, with a size check at 64 and 128 pixels.
AI coat of arms or crest as a transparent PNG, with alpha check
Generate a family crest or team badge as a transparent PNG with gpt-image-2.5's background parameter, then verify the alpha channel before it goes on merch.
Privacy policy update explainer: a 40-second avatar video
Explain a privacy policy change in 40 seconds with a Sume avatar: three scenes, captions on, legal review before render. Cost by tier and a script checklist.
AI Polaroid or VHS photo look on your own photo: an edit call
Give a photo the Polaroid or VHS look with one reference edit instead of a filter, then draw the date stamp or caption in code so the digits are exact.
Real estate agent intro clip: headshot, logo and listing photos
Send a headshot, your logo and listing photos as reference_image_urls to Gemini Omni Flash 1.1 and address each as <IMAGE_REF_n> for a 3 to 10 second intro.
Event RSVP clips: invitation, reminder and last call from one avatar
Plan three Sume avatar clips for one event, an 18-second invitation, a 10-second reminder and an 8-second last call. 36 seconds total costs $6.62 on Standard.
Make a shop mascot copy a dance: Genjutsu source video and images
Genjutsu on the Video Router takes one source video_url and 1 to 8 reference images, 4 to 30 seconds at 480p or 720p. It has no text-only mode.
2-second YouTube intro sting: Wan 3.0 has the lowest floor
The shortest clip length Sume's docs list for the Video Router is 2 seconds on wan-3.0. Seedance 2.5 starts at 4. Here is a request and how to trim for less.
Lab demo video to worksheet stills: video frames at up to 24 times
Turn a recorded lab demo into a step-by-step worksheet: video-frames takes 1 to 24 at values from a clip of 300 seconds or less and returns full-size stills.
Board game trailer: table clips and box art as Gemini Omni references
Use up to 3 short clips (3 s or less each) plus images as references in Gemini Omni Flash 1.1 to make a 10-second board game trailer with native sound.
AI paper doll cutouts: transparent outfits that fit one body, via API
Make paper-doll dress-up pieces: one body pose as the anchor, each outfit as a transparent PNG using the body as a reference, then print them at a shared scale.
AI vinyl sleeve art at 12 inches: gpt-image-2.5 stops at 240 dpi
A 12-inch square sleeve face at 300 dpi is 3,600 pixels square, but gpt-image-2.5's largest square is 2880, or 240 dpi. Your options for the last 60 dpi.
AI blog featured image at 16:9: 1536x864 passes, 1920x1080 does not
For a 16:9 blog featured image, gpt-image-2.5 accepts 1536x864 and 2048x1152 but not 1920x1080, because 1080 is not a multiple of 16. Checked in a table.
School closing announcement as a 30-second avatar video with captions
Turn a snow-day notice into a 30-second captioned avatar video in a 9:16 frame. Standard is the fastest Sume tier; cost by tier and a send-ready script.
AI chibi figurine from a photo: one reference edit, four takes
Turn a portrait into a glossy chibi figurine render with one reference edit on gpt-image-2.5, four takes per call, and a plain background for the cutout.
AI action figure box from a selfie: a gpt-image-2.5 reference edit
Make the AI action-figure-in-a-box image from one selfie: send it as an input reference to gpt-image-2.5, then letter the name on the box in code.
Restaurant promo clip: keep Gemini Omni's native audio or swap it
Gemini Omni Flash 1.1 always makes synced audio. Keep it, or drop it with video trim ($0.02) and lay a Timeline soundtrack under the picture.
AI pet portrait in a costume: keep the markings with a reference
Put your dog or cat in a regal costume portrait: one pet photo as an input reference, a keep-the-markings prompt, and a retry plan for the coat pattern.
Quinceañera invitation teaser: portrait and venue as references
A 10-second quinceañera invitation teaser from up to 10 reference images with Gemini Omni Flash 1.1, with the date added as a plate instead of generated text.
AI nail art preview from a hand photo: a mask_url edit on one finger
Preview a nail design on a client's hand photo with a mask_url edit on gpt-image-2.5: a mask limited to the nails, a reference for the design, and edge checks.
Agency approval loop for AI video: 480p proof, then the final on Sume
Show clients a cheap 480p Seedance 2.5 proof, get sign-off, then pay for the 1080p final. Cost table for a 30 s clip: $8.06 proof, $42.65 final, plus rounds.
App preview clip from screenshots with Seedance 2.5 and a caption pass
Screenshots as reference images can drive a 15 s Seedance 2.5 app promo on Sume for $8.67 at 720p. Generated UI text is unreliable, so add words after.
Dubbed video: burn target-language captions with script_text
After dubbing into Spanish or German, caption the new audio with your translated script as script_text so burned words match your approved translation.
Children's story clip from one illustration: Seedance 2.5 or 2.0
Animate one storybook illustration with a Seedance reference image on Sume. A 15 s page is $5.67 on Seedance 2.0 and $8.67 on Seedance 2.5.
Does dimming or cropping a clip need a YouTube AI label?
YouTube lists dimming as a colour adjustment needing no label; cropping is not listed either way. The label turns on realistic synthetic content.
Music bed for a SaaS product demo: a Lyria brief and ducking
A product demo needs a quiet instrumental bed under narration. A seven-axis Lyria 3.5 brief, a Timeline soundtrack with duck_db, and what it costs.
Music clip with Seedance 2.5: audio reference plus performer image
A Seedance 2.5 request on Sume takes reference_audio_urls only with a reference image or video. Build a 15 to 30 s music-driven clip and see the cost.
Muted product loop in four languages: burn captions from cues
A silent clip fails speech-to-captions as caption_no_speech. Pass cues with text, start and end to burn four translations at $0.20 a job.
One video in three languages: per-language voiceover tracks on Sume
Render scene lines in each language with TTS, join each language into one track with timeline audio concat, then re-base scene starts from segments[].
Online course trailer in 30 seconds with Seedance 2.5: beats and cost
A 30-second course trailer in one Seedance 2.5 request: beats for hook, promise and call to action, authored captions on top, about $17.33 at 720p on Sume.
Podcast teaser clip: cover art plus audio reference on Seedance 2.5
Make a 15 to 30 s teaser by sending cover art and an episode excerpt as reference_audio_urls to Seedance 2.5 on Sume. Honest lip-sync limits and cost.