Seedance 2.0 Fast Reference To Video
Fast Seedance 2.0 reference-to-video generation using text plus optional image, video, and audio references.
Fast Seedance 2.0 reference-to-video generation using text plus optional image, video, and audio references.
Model Overview
Seedance 2.0 Fast Reference To Video generates short video clips from a prompt and optional reference media. It supports image, video, and audio references, 480p and 720p output, 4-15 second duration controls, flexible aspect ratios, and optional generated audio.
Best At
- Fast multimodal video drafts with reference images, videos, or audio.
- Prompt-directed clips that borrow subject, style, or motion cues from supplied media.
- Reference-heavy creative exploration where speed matters.
Limitations / Not Good At
- Reference files must be aligned with prompt instructions to avoid conflicting guidance.
- Video-reference pricing includes input video duration as well as output duration.
- Fast mode prioritizes turnaround over maximum final polish.
Ideal Use Cases
- Creating video variations from visual and audio reference sets.
- Testing subject, style, or motion references before final generation.
- Generating short campaign and storyboard clips with multimodal guidance.
Input & Output Format
- Input: required
prompt; optionalimage_urls,video_urls,audio_urls,aspect_ratio,duration,resolution,generate_audio, andseed. - Output: generated video URI returned on
response.
Performance Notes
- Pricing scales with generated video size and duration.
- Runs with video references also account for input video duration, with Fal applying its video-input multiplier.
Prompt
StringText prompt describing the generated video and how to use references.
Reference Images
StringReference images for subject, style, or scene guidance.
Reference Videos
StringReference videos for motion, style, or scene guidance.
Reference Audio
StringReference audio for audio-guided video generation.
Prompt
StringText prompt describing the generated video and how to use references.
Duration
StringVideo duration in seconds, or auto to let the model decide.
autoResolution
StringVideo resolution. 480p is faster and cheaper; 720p has more detail.
720pAspect Ratio
StringAspect ratio of the generated video.
autoGenerate Audio
BooleanGenerate synchronized audio for the video.
trueSeed
NumberRandom seed. Leave at -1 for a random result.
Output
InferredGenerated video output.
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / BytedanceInput
Output