Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Replace the view outside a window in an interior photo
Swap the scene seen through a window and keep the curtains, frame and room, then relight in a second pass. Ideogram 4.5 on Sume, with prompts and costs.
Idempotency-Key from an order id and version, never a fresh uuid
A fresh uuid per request makes Idempotency-Key do nothing. Derive it from the order id plus a version you bump only to re-run. Scope: one Format, 255 chars.
Three characters, three dances: Omni IMAGE_REF and VIDEO_REF tokens
Google's Omni 1.1 demo swaps three dancers for a dog, an octopus and a bear. Here is the same request on Sume, with the 0-based reference tokens in order.
sume jobs cancel needs --confirm-submit, and only queued jobs cancel
Sume CLI cancel is a write: sume jobs cancel <job_id> --confirm-submit. It works only before generation starts; later: 409 job_generation_already_started.
Price per kept AI clip when 1 in 3 is rejected: Wan 720p
A 15-second Wan 3.0 clip at 720p is $1.875 on Sume. If you keep one clip in three, the real price per kept clip is $5.625. The keep rate is a budget input.
Which URL does each Sume media tool accept: public or media.sume.com?
Video captions and face swap take a public HTTPS URL; trim, filter, frames, inspect, detach, compose and timeline need your workspace's media.sume.com file.
Animate 12 storybook pages as 5-second clips: Omni or MiniMax H3
A picture book with 12 illustrated pages, each animated for 5 seconds. Price per book on Gemini Omni Flash 1.1 and MiniMax H3 on Sume, and the input each takes.
Does Wan 3.0 do 4K? Claim check against vendor pages and Sume
Alibaba lists 480p, 720p and 1080p for Wan 3.0, Morphic says no 4K, and Sume rejects 4k for wan-3.0. Where 4K exists on Sume and at what clip length.
Cancel a wrong video job after a Sora port: only before it starts
Ported prompts on the wrong model burn money. Sume cancels a video job only before generation starts; later you get 409 job_generation_already_started.
video-frames returned a null url: the job succeeded, one frame failed
If one instant fails to extract, video-frames sets that frame's url to null and the job still completes. How to detect it and retry only that time.
Crop a 2:1 landscape phone recording to 9:16: width 0.28125
A 2:1 (18:9) landscape clip needs width 0.28125 for 9:16: exact at 1920x960 (540x960), 606 px at 2160x1080. The offset, the rounding and the full request.
video-filter unsupported_filter_op_field: crop and dim keys allowed
A crop op takes four fractions and dim takes one amount; any extra key returns unsupported_filter_op_field. The exact key lists and where the extra work goes.
jq one-liner: export Sume bulk queue items to CSV by index
Turn the bulk queue receipt from a curl poll into CSV rows of index, status, run_id and error code with jq, then paste them next to your SKU column.
Scam alert video for customers with an AI avatar: script rules
If scammers use your name, a 20-second avatar clip can warn customers. Script rules, the AI label, why it cannot verify anything, and cost by tier.
Change the name and number on a jersey photo, keep the lettering
Edit the name and number on a jersey or sign photo with Ideogram 4.5 on Sume: the prompt wording, the reference rules and what a low-tier test costs.
Check an Omni edit's length with video-inspect before a timeline join
An edit should follow the source length. Confirm it with a probe-only video-inspect call before the clip goes into a Timeline render, with a Python read.
Check an Omni edit kept the rest of the clip: video-frames pairs
Compare stills from the source and the edited clip at the same timestamps with video-frames on Sume. A script that submits both extracts, plus what to look for.
Validate Wan 3.0 reference limits in Python before submitting
wan-3.0 takes 10 images, 5 videos (15 s total, 16 fps minimum) and 5 audios (15 s total). A short Python check catches an over-limit manifest early.
Four characters, two locations: a Wan 3.0 series bible in ten images
Wan 3.0 on Sume takes 10 reference images per job. Spend them as four characters at two views each plus two sets, and reuse the same set for every episode.
Photo to talking selfie clip: put the spoken line in the Omni prompt
fal's Omni 1.1 example ends its prompt with a quoted spoken line. Here is that pattern on Sume from a still, the cost of 6 seconds, and a transcript check.
Destination film from ten location photos with Wan 3.0 on Sume
Turn ten photos of a town into a 30-second film with wan-3.0 reference images: $3.75 at 720p, $7.50 at 1080p, and a prompt that needs a dawn-to-dusk arc.
Reuse one sentence twice: timeline audio split allows overlaps
Timeline audio split takes up to 20 ranges that may overlap, so one hook sentence can open and close a video without re-recording or re-synthesising it.
A 2.5% word error rate is 25 wrong words per 1,000: plan the proofread
If a 2.5% WER held on your audio, a 1,000-word transcript would still carry about 25 wrong words. How to proofread and burn captions on Sume with script_text.
gemini-3.1-flash-image is deprecated: move to Nano Banana 2.1
Google deprecated gemini-3.1-flash-image on Oct 6 with no shutdown date and named gemini-nano-banana-2.1 as the replacement. What to change, and what Sume does.
Nano Banana Pro vs 2.1: 4x the price at 1K, 2.1x at 4K
Google lists Nano Banana Pro at $0.134 per 1K or 2K image and $0.24 at 4K, against $0.0336, $0.0504 and $0.113 for Nano Banana 2.1. When Pro still pays.
One Sume image upscale costs the same as 22 seconds of video upscale
Sume image upscale is $0.20 per image and video upscale is $0.009 per second, so one image upscale buys 22.2 seconds of video. A cutout is $0.0225.
Nano Banana 2.1 has no 512px size in Google's guide; Sume lists 512
Google's guide says 512px is unsupported on Nano Banana 2.1, yet Sume's catalog enum for it starts at 512. How to test what a call returns.
Nano Banana 2.1 references: 10 objects, 4 characters vs Pro 6, 5, 3
Google splits Nano Banana 2.1 references into 10 objects and 4 characters, and Pro into 6 objects, 5 characters and 3 style images. How Sume's flat list maps.
Gemini Omni Flash 1.1 on Runway: 3.4 to 30 credits vs Sume
Runway prices Gemini Omni Flash 1.1 at 3.4 credits a second at 360p up to 30 at 4K, at $0.01 a credit. Sume's per-second rates at the same ends.
Runway's two Omni Flash ids: 10-11 credits vs 3.4-30 for 1.1
Runway lists gemini_omni_flash at 10 to 11 credits a second and gemini_omni_flash_1.1 at 3.4 to 30. Which is cheaper depends on resolution.
mask_url on ChatGPT Image 2: not listed, only the 2.5 rows take it
Sume lists mask_url only on ChatGPT Image 2.5 Flare and Sunburst. Sending it to ChatGPT Image 2 is rejected. What to do for a masked edit on the older row.
Photo to watercolor with ChatGPT Image 2: one reference, one prompt
The Sume docs use ChatGPT Image 2 with one reference photo and the prompt "make this scene look like a watercolor painting". The request and what to check.
Crop 9:16 to 2:3 for Pinterest: height 0.84375, then 1000x1500
A 1080x1920 clip becomes 1080x1620 (2:3) with a crop of height 0.84375. Pinterest's page recommends 1000 x 1500 for Showcase and Collections video.
Crop 3:4 to 2:3 for Pinterest: width 0.8889, x 0.0556 centered
A 1080x1440 clip becomes 960x1440 (2:3) by cropping width to 0.8889. Pinterest recommends 2:3 for Showcase and Collections; here are the numbers and request.
Creatify max video length: 2 min on Starter, 10 on Pro, vs Sume
Creatify's page caps Starter videos at 2 minutes and Pro at 10. Sume caps one avatar job at 60 seconds, so 10 minutes is ten jobs: $110.40 to $330.00.
Colossyan NEO vs NEO2 minutes: 20 and 0.5 on Starter, 30 and 10 on Pro
Colossyan lists two monthly minute pools, NEO and NEO2: 20 and 0.5 on Starter, 30 and 10 on Professional. How to compare that with Sume per second.
Crop 9:16 to 4:5 for Facebook feed: height 0.703125, y 0.148
A 1080x1920 clip becomes 1080x1350 (4:5) with a crop of width 1 and height 0.703125. Meta's Facebook feed page lists 4:5 at 1440x1800; here is the request.
Crop a 2:3 Pinterest video to 4:5 for Facebook: height 0.8333
A 1000x1500 Pinterest video becomes 1000x1250 (4:5) with a crop of height 0.8333. Facebook's feed page lists 4:5 at 1440x1800; request inside.
Is Gemini 3.8 Flash TTS in the Live API? No, per Google's model page
Google's model page marks the Live API unsupported for Gemini 3.8 Flash TTS. For live voice use Gemini 3.8 Live; Sume TTS is for async audio jobs.
Where can you use Gemini 3.8 Flash TTS today? API, Notebook, Vids
Google lists Gemini 3.8 TTS in the Gemini API, AI Studio, Gemini Notebook and Google Vids now; the Enterprise API is coming soon. What Sume offers instead.
HappyHorse 1.1 on Cloudflare: 2,500-character prompt limit
Cloudflare's HappyHorse 1.1 text-to-video page caps the prompt at 2,500 characters and clips at 3 to 15 seconds. HappyHorse is not in the Sume catalog.
HappyHorse 1.0 vs 1.1: which one renders 480P on Model Studio?
On Alibaba Model Studio only HappyHorse 1.1 lists 480P. Both versions take 3 to 15 seconds, and 1.0 adds a video-edit id. Neither is in Sume's catalog.
Crop 4:5 to 1:1 for a TikTok ad: height 0.8 and the 640x640 minimum
TikTok's in-feed page lists 1:1 with a 640x640 minimum. A 1080x1350 feed clip crops to 1080x1080 with height 0.8, y 0.1 centered, then clears it easily.
Is 4:5 allowed as a TikTok in-feed ad? The page lists three ratios
TikTok's in-feed spec lists 9:16, 16:9 and 1:1 for non-Spark ads, not 4:5. Crop a 4:5 master to 1:1, or build a 9:16 canvas with Sume Timeline.
Seedance 2.5 on Runway at 20 to 68 credits a second vs Sume tokens
Runway prices seedance2_5 at 20 to 68 credits a second plus input fees, or $0.20 to $0.68. Sume bills Seedance 2.5 per 1,000 video tokens instead.
Seedance 2.5 Draft mode on Runway: 480p proofs, and 480p on Sume
Runway's Oct 2 changelog adds Seedance 2.5 Draft mode for 480p drafts. Sume's seedance-2.5 also renders at 480p through its API; here is how they differ.
MAI-Voice-2.1 has three style lists: emotion, role and expressive
MAI-Voice-2.1 styles come in three vocabularies: 19 emotions, 6 roles and 11 expressive tags. Which voices use the expressive set, and how Sume differs.
MAI-Voice-2.1 whispering and shouting: the 19 voices that list both
Only 19 MAI-Voice-2.1 voices list whispering and shouting by our count. English-UK and Korean voices do not. Sume has no whisper switch.