Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
OpenAI Agents empty tool arguments: Sume no-argument tools
Agents SDK 0.22.1 fails closed on empty tool arguments. Sume's no-argument tools take {}, while paid tools need idempotency_key and cannot run empty.
OpenAI Agents SDK tool not found: what a Sume call returns
A hosted MCP tool name that differs only in - or _ gets a tool_not_found result with a Did you mean hint; a scope-hidden tool returns insufficient_scope.
Always-on agents making video: a Sume callback_url, not polling
An always-on agent that waits on video should not poll in a loop. On Sume, pass an HTTPS callback_url and receive a signed webhook when the job finishes.
OpenRouter Security Center key sprawl: a Sume key checklist
OpenRouter's Security Center flags idle keys and missing limits. For Sume, rotate by replace, verify, revoke, and use per-call max_spend_usd and key budgets.
Pika Camera Director vs a prompted video edit on Sume
Pika Camera Director reshoots a scene from new angles. On Sume, Omni Flash 1.1 edits a clip from a video_url and a prompt; there is no camera-angle parameter.
Pika Soundtrack: video in, sound out. What Sume has instead
Pika Soundtrack scores a finished video. Sume's docs offer generate_audio at video creation and a Timeline soundtrack bed, but no video-to-sound endpoint.
30-second video with sound: Pika Video Studio vs Sume ids
Pika Video Studio makes up to 30 seconds with sound. On Sume, seedance-2.5 and wan-3.0 reach 30 seconds; every other catalog model stops at 15.
Pika Video Studio's 50 references vs Sume's per-model limits
Pika Video Studio attaches up to 50 references. Sume's caps are per model: 10 images and 3 short clips on Omni Flash, 1 to 8 images on Genjutsu.
Pinterest Performance+ Priority Products: build a creative set
Priority Products lets Performance+ favor chosen products for a seasonal launch. Make a 2:3 image set for those few products, not the whole catalog.
Pinterest A/B testing: two Pin creatives from one reference image
Pinterest's self-serve A/B test compares creative or targeting. Change one thing between two Pin images made from the same reference with Sume.
Qwen Image 2.1: when you must show Built with Qwen
The Qwen Research License requires Built with Qwen or Improved using Qwen when outputs train a distributed model, and bars Qwen as a derivative's main name.
Qwen-Image 2.1 ControlNet Union Fun in ComfyUI vs reference images
ComfyUI added Qwen-Image 2.1 ControlNet Union Fun for editing on 2026-09-29. Sume has no ControlNet input; it edits with reference images and masks.
Qwen Image 2.1 LoRA redistribution: notice file and Hangzhou courts
Sharing Qwen-Image-2.1 weights or a LoRA needs the license copy, modified-file notices and a Notice file; disputes go to the Hangzhou courts. Clause summary.
Qwen Image 2.1 license: research only, commercial needs a request
Qwen-Image-2.1 ships under the Qwen Research License: non-commercial means research or evaluation only, and commercial use needs a separate license.
Restyle a clip longer than 30 seconds: trim, then Genjutsu
Genjutsu takes 4 to 30 second sources. For a longer clip on Sume, cut ranges with video trim, restyle each range, then join them with Timeline.
Reuse one winning ad across a catalog: one edit job per SKU
To reuse a proven video ad for many products on Sume, send one edit job per SKU with its own Idempotency-Key, and submit in waves so queue_full never hits.
Runway Ad Localization recipe vs a Sume image edit prompt
Runway localizes an ad image from a targetLanguage code like ja. On Sume, send the ad as a reference image and name the language in the edit prompt.
Runway ASSET.INVALID vs Sume validation and unreachable media
Runway's ASSET.INVALID covers any unacceptable input media. Sume separates validation errors from fetch failures, and one 502 is still your input to fix.
Runway Compositing Nodes vs Sume Timeline compose
Runway added compositing nodes to blend images and video in Workflows. Sume's Timeline compose puts one still and one video in one MP4: stack or overlay.
Runway failureCode is diagnostic: what to show users from Sume
Runway says not to show SAFETY failure codes to users. On Sume, show your own text keyed on code; keep message, request_id and details in logs.
Runway INTERNAL.BAD_OUTPUT.01: fix the prompt, then resubmit
Runway's INTERNAL.BAD_OUTPUT.01 may succeed after prompt fixes. Sume's equivalent step: inspect job events, fix the input, and send a new request.
Runway INTERNAL or null failureCode: how long to delay a retry
Runway says to add a delay for INTERNAL or null failure codes but gives no number. Sume's errors carry retryable and retry_after_seconds fields.
Runway MCP workflows vs Sume hosted MCP tool chains
Runway MCP can now list, open and run saved workflows from chat. Sume's hosted MCP exposes single tools you chain with jobs_wait and an idempotency_key.
Runway Product Ad recipe vs Sume reference-to-video
Runway's Product Ad Recipe turns product photos into an ad video. On Sume, send photos as reference images and put the concept in one prompt.
Runway product swap vs a Sume prompted video edit
Runway's Product Swap Recipe takes a video plus product images. Sume's closest route is one edit call: a video_url and a prompt that names the swap.
Reference media guidelines: Runway Recipes and Sume checks
Runway's guide says strong references drive quality. On Sume, add the checks the docs list: public HTTPS URLs, per-model reference types, 3-second video refs.
Runway SAFETY.INPUT credits not refunded: what Sume does
Runway does not refund credits for SAFETY.INPUT failures. Sume's docs describe one rule for failed jobs: the reservation is released or refunded.
Runway THIRD_PARTY.UNAVAILABLE: retry rules vs Sume's codes
Runway says not to retry THIRD_PARTY.UNAVAILABLE immediately. On Sume, generation_unavailable means retry later; provider_capacity_exceeded keeps the key.
Shopify collection.products trigger: one Sume job per product added
Shopify Events' collection.products trigger fires when a product joins or leaves a collection. Key one Sume image job on collection and product ids.
Shopify Events fields_changed: only added should start a Sume job
Shopify Events' fields_changed is now an object with added, updated and removed. Start a paid Sume job from added only, and key it so replays are safe.
Shopify Events query_filter: ACTIVE products only for Sume runs
Shopify Events' query_filter can limit deliveries to ACTIVE products. Filter at Shopify so draft products never reach a Sume submit or a bulk queue.
Shopify's Meta AI channel: product image variants from Sume
Shopify now lists Meta as an AI channel and shares products through Shopify Catalog. Here is what Sume can make for those listings: image variants and a video.
Holiday jingle for ads: Spotify says listening starts in October
Spotify reports holiday listening already underway on Oct 1. Make a holiday music bed for an ad with the Music Router, steering length in the prompt.
Synthesia Assistant styles vs Sume's scene prompt and previews
Synthesia Assistant asks for a Cinematic or Presentation delivery style before scenes generate. Sume uses scene direction plus first-frame previews instead.
Synthesia Express-3 follows script sentiment; Sume's script controls
Synthesia Express-3 avatars follow script sentiment. Sume Avatar Video is steered by script text, silence beats, scene direction and quality tiers.
Synthesia Interactive Avatar and LiveKit: Sume's job-based pieces
Synthesia's Interactive Avatar API runs on a LiveKit plugin with your own LLM and STT. Sume offers job pieces: TTS, speech to text and still-plus-audio clips.
Synthesia Style Avatars from a prompt: the Sume avatar input types
Synthesia's Avatar Builder makes Style Avatars from a prompt and a preset. Sume creates avatars from a Prompt, a Profile or an Image, one job per avatar.
Tavus 50 new Phoenix-4.5 stock faces vs a Sume avatar handle
Tavus added 50 first-party Phoenix-4.5 stock faces, 28 of them Pro. On Sume you create your own avatar from a prompt, profile or image and reuse its handle.
Tavus disclosure_type controls vs Sume authored caption cues
Tavus added disclosure_type, verbal_disclosure and visual_disclosure for EU AI Act use. Sume has no such setting; authored caption cues can burn a line of text.
Tavus recording storage key_template vs Sume media URLs
Tavus can write recordings to S3, GCS or Azure Blob. Sume returns finished files as media.sume.com artifact URLs, delivered by webhook or job result.
Concatenate audio files by API: parts, and no top-level url
Sume Timeline audio concat needs a parts array and refuses a top-level url or ranges. Each operation accepts its own keys; mixing them returns a stable code.
Split audio into segments by timestamps: url and ranges
Sume Timeline audio split needs a top-level url and 1 to 20 ranges. A range with end at or before start is refused; each segment gets its own audio_url.
Image over video longer than the clip: compose's 300 s ceiling
Sume Timeline compose length comes from the video layer, capped at 300 seconds. Asking for more than the file clamps with a warning and the job still succeeds.
compose_image_not_still and compose_video_not_video: the fix
Sume Timeline compose probes both URLs: image.url must be a still, video.url a video. Failing either refuses the request; off-host URLs need an import first.
Image above video, or left and right: compose image_region axes
In Sume Timeline compose a horizontal split takes top or bottom and a vertical split takes left or right; a mismatch is a 400, compose_image_region_wrong_axis.
Overlay an image on a silent video: compose warns, keeps audio
A silent video in Sume Timeline compose is a compose_video_has_no_audio warning, not a failure. Audio passes through when present; Timeline supplies it later.
Change frame rate when compositing: output_fps_resamples_sources
Sume Timeline compose defaults to the video layer's own frame rate. Set output.fps to a different rate and it warns output_fps_resamples_sources.
Add an image over a video: position, width_ratio, margin_ratio
Sume Timeline compose overlay places a still with position top, center or bottom, width_ratio 0.05 to 1 (default 0.9) and margin_ratio 0 to 0.45 (default 0.05).