sam-3/video-to-video
Empowers precise tracking and seamless object edits across video scenes.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Scene description using your references as cues |
| images | No | array (image URIs) | — | 0–9 | Reference images for look and identity |
| videos* | Yes (*) | array (video URIs) | — | 1–3 | Reference clips for motion and rhythm (at least one required) |
| audios | No | array (audio URIs) | — | 0–3 | Reference audio for mood and pacing |
| aspect_ratio | No | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive | Output frame ratio |
| duration | No | integer | 5 | 4–30 (seconds) | Clip length |
| generate_audio | No | boolean | true | true / false | Native synchronized audio |
Billing uses total counted video seconds (reference video duration + output duration) at:
Image and audio references are not billed as duration.
Empowers precise tracking and seamless object edits across video scenes.
Create structured cinematic clips with audio, scene links, and prompt accuracy
Bridge start and end stills into smooth cinematic video
Generate cinematic 3-15s videos from text with optional sound.
Generate realistic videos with synced audio from text using OpenAI Sora 2.
Animate an image into a high quality video with OpenAI Sora 2 Pro.
Seedance 2.5 Reference to Video 1080p is a ByteDance reference-to-video endpoint that guides a 1080p clip with images and optional video or audio. It fits consistent characters, products, and style-locked brand finals.
The workflow is the same multi-reference path; Seedance 2.5 Reference to Video 1080p locks output at 1080p for sharper delivery. Validate reference stacks at lower resolution first, then reuse them here.
Seedance 2.5 Reference to Video 1080p accepts up to 9 reference images, 3 reference videos, and 3 reference audio files, with duration from 4 to 30 seconds (default 5). Aspect ratio options include adaptive and common fixed ratios.
Seedance 2.5 Reference to Video 1080p is billed at $0.53 per second on total counted video seconds: reference video duration plus output duration. Image and audio references are not billed as duration.
Yes. Prototype in the RunComfy model UI, then call the same Seedance 2.5 Reference to Video 1080p template through the RunComfy API with matching parameters. Generations consume usd / credits on both paths.
No. Seedance 2.5 Reference to Video 1080p can run from a prompt plus images alone. Add short reference videos or audio when you need stronger motion or mood guidance.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
