seedance-2.5/reference-to-video/720p
Seedance 2.5 Reference to Video: Turn reference images, videos, and audio into cinematic AI video
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | A lone cyclist crosses a rain-swept bridge at blue hour as the camera tracks alongside, reflected city lights shimmering below, cinematic lighting, natural motion. | Free input | Describe the scene, action, camera movement, and how references should guide the result. |
| images | No | array | Example reference | Up to 7 items | Image URLs used to guide subjects, objects, or visual identity. |
| videos | No | array | None | Free input | Optional video URLs used to guide motion or appearance; video-reference runs use the documented 2x rate. |
| aspect_ratio | No | string | 16:9 | 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9 | Frame shape for the generated video. |
| resolution | No | string | 720p | 360p, 540p, 720p, 1080p | Output quality tier shown as video resolution. |
| duration | No | integer | 5 | 1-15 | Requested output duration in seconds, from 1 through 15. The upstream API may use 0 when video references determine timing; the UI exposes 1-15 for image-only mode. |
| generate_audio_switch | No | boolean | false | Free input | Generate an optional native audio track with the video. |
| seed | No | integer | 0 | Free input | Seed used to reproduce or vary a generation. |
[Limited Time Offer] Half price. Audio and 1080p are included at no extra cost. Billing is per generated second.
| Resolution | Price |
|---|---|
| 360p | $0.015/s |
| 540p | $0.020/s |
| 720p | $0.025/s |
| 1080p | $0.025/s |
Turning audio on does not change the rate. After this Limited Time Offer ends, regular rates start at $0.049/s for 720p and $0.094/s for 1080p.
When one or more video references are supplied, each rate above is doubled. Image-only references use the rates in the table.
Seedance 2.5 Reference to Video: Turn reference images, videos, and audio into cinematic AI video
Guide new video with image or video references and text direction.
Reanimate expressive faces from sound cues with precise 4K video edits
Streamline scene design with high-fidelity, auto-interpolated video
Convert static visuals into seamless motion clips with audio control.
High-speed text-to-motion generator for cinematic storytelling use.
PixVerse C1 Reference To Video is configured for reference to video generation with prompt direction, output controls, and an optional audio track. Outputs can run from 1 to 15 seconds at 360p, 540p, 720p, or 1080p.
PixVerse C1 Reference To Video fits filmmakers, technical artists, designers, agencies, and product teams creating shot concepts, campaign assets, product motion, or social video. It is especially useful when prompt-level direction and repeatable parameters matter.
Give PixVerse C1 Reference To Video separate instructions for subject action and camera movement, then add framing, lighting, atmosphere, and pacing. Keep the requested action realistic for the selected 1-15 second duration.
PixVerse C1 Reference To Video includes a generate_audio_switch option that is off by default. Turning it on requests native audio and does not change the per-second rate.
PixVerse C1 Reference To Video exposes 360p, 540p, 720p, and 1080p, with an integer duration from 1 through 15 seconds. Available aspect-ratio control depends on the task form.
PixVerse C1 Reference To Video includes a seed parameter for controlled iteration. The same seed and inputs can improve repeatability, although generated-video systems may still show some variation.
Yes. Teams can test PixVerse C1 Reference To Video in the RunComfy model UI and then send the same exposed parameters through the HTTP API. This supports moving a validated request into an application or automation workflow.
PixVerse C1 Reference To Video is billed per generated second. Limited Time Offer rates are $0.015/s at 360p, $0.020/s at 540p, and $0.025/s at 720p or 1080p, with or without audio. Video references double these rates. Your total depends on duration.
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.
