New — access 450+ AI models through one unified API.Start building free

seedance-2.0-mini/reference-to-video-spicy

Seedance 2.0 Mini Spicy Reference to Video is ByteDance's faster, lower-cost reference-to-video model for cinematic multi-shot videos. It generates narrative sequences guided by up to 12 reference files spanning images, videos, and audio clips with AI camera control, consistent characters, 480P / 720P output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

reference-to-video$0.6000/ run

Prompt

0/2000
Reference MediaImages, videos, and audio supported
PreviewJSON

Your result will appear here

Write a prompt and hit Generate.

Related models

seedance-2.5 / image-to-videoimage-to-video
seedance-2.5 / image-to-video

Seedance 2.5 (Image-to-Video) turns a reference image and prompt into native cinematic video up to 30 seconds, with up to 50 full-modal reference assets, richer editing control, and native audio-visual synchronization. Built on ByteDance's next-generation Seed architecture, it preserves the input image's subject and composition while adding expressive, physically accurate motion.

Seedance$0.7600
seedance-2.5 / text-to-videotext-to-video
seedance-2.5 / text-to-video

Seedance 2.5 (Text-to-Video) generates native cinematic video up to 30 seconds directly from a prompt, with native audio-visual synchronization and stronger precision in editing and generation control than Seedance 2.0. Built on ByteDance's Seed architecture for production-ready creative workflows.

Seedance$0.7600
seedance-2.5 / reference-to-videoreference-to-video
seedance-2.5 / reference-to-video

Seedance 2.5 (Reference-to-Video) generates video guided by up to 50 full-modal reference assets spanning images, videos, and audio clips. Use @Image1, @Video1, @Audio1 tags in your prompt to assign roles — style transfer, lip-sync, motion transfer, and multi-scene composition across native 30-second clips at up to 1080p.

Seedance$0.7600
seedance-2.0 / image-to-video15% OFFimage-to-video
seedance-2.0 / image-to-video

Seedance 2.0 (Image-to-Video) generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it preserves the input image's subject and composition while adding expressive, physically accurate motion.

Seedance$0.4080$0.4800
seedance-2.0 / text-to-video15% OFFtext-to-video
seedance-2.0 / text-to-video

Seedance 2.0 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.

Seedance$0.4080$0.4800
seedance-2.0 / reference-to-video15% OFFreference-to-video
seedance-2.0 / reference-to-video

Seedance 2.0 (Reference-to-Video) generates cinematic videos guided by up to 12 reference files spanning images, videos, and audio clips. Use @Image1, @Video1, @Audio1 tags in your prompt to assign roles — style transfer, lip-sync, motion transfer, character consistency, and multi-scene composition. Supports 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance$0.4080$0.4800

Seedance 2.0 Mini Reference To Video Spicy

Seedance 2.0 Mini Spicy Reference to Video is ByteDance's faster, lower-cost reference-to-video model for cinematic multi-shot videos. It generates narrative sequences guided by up to 12 reference files spanning images, videos, and audio clips with AI camera control, consistent characters, 480P / 720P output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Key Features

  • Animate still images into smooth, high-quality video with natural motion.
  • Faithful to the source — preserves subject identity, composition and visual style during animation.
  • Prompt-guided motion — control camera movement, subject actions and scene dynamics via text.
  • Multiple duration options — generate clips from a few seconds up to the model maximum.
  • Resolution support — 480p and 720p.
  • Consistent physics — realistic motion with proper object dynamics and lighting continuity.

Parameters

ParameterRequiredDescription
promptYesText description of the motion and scene dynamics.
imageYesSource image URL to animate.
durationNoVideo length in seconds (default varies by model).
aspect_ratioNoOutput ratio: 16:9, 9:16, 4:3, 1:1 (default: matches input).
resolutionNoOutput resolution: 480p, 720p (default: 720p).

How to Use

  1. Upload a high-quality source image that you want to animate.
  2. Write a prompt describing the desired motion — camera movement, subject action, and mood.
  3. Set duration and resolution based on your needs.
  4. Generate and download your animated video clip.

Code Examples

import os
import requests

response = requests.post(
    "https://aircube.ai/api/v3/seedance-2.0-mini/reference-to-video-spicy",
    headers={
        "Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
    "prompt": "Camera slowly orbits around the subject, hair flowing gently in the breeze",
    "image": "https://example.com/portrait.jpg",
    "duration": 5
},
    timeout=300,
)
data = response.json()

if data["success"]:
    print("ID:", data["data"]["id"], "Status:", data["data"]["status"])
else:
    print("Error:", data["error"]["message"])

Pricing

ResolutionDurationCost
480p4s$0.14
480p5s$0.18
480p6s$0.22
480p8s$0.29
480p10s$0.35
480p12s$0.43
480p15s$0.53
720p4s$0.38
720p5s$0.47
720p6s$0.56
720p8s$0.75
720p10s$0.94
720p12s$1.13
720p15s$1.41

Billing rules

  • 480p / 4s: $0.14.
  • 720p / 4s: $0.38.
  • Longer durations scale proportionally.
  • First 5 reference images are free; each additional image adds $0.04.
  • Reference videos and audio do not add extra charges.
  • Failed generations are not charged.

Best Use Cases

  • Product animation — bring still product shots to life with subtle motion.
  • Social media content — create eye-catching animated posts from static images.
  • Ad creatives — transform hero images into engaging video ads.
  • Character animation — animate character art or portraits with expressive motion.
  • Scene storytelling — extend a keyframe into a full cinematic sequence.

Pro Tips

  • Upload high-resolution, clean images for best motion quality.
  • Describe camera movement (zoom in, pan left, orbit around) for cinematic results.
  • Start with short durations (3-5s) to iterate quickly, then extend for final renders.
  • Keep the subject centered in the source image for more stable animation.
  • Mention specific actions (walking, waving, flowing) for directed character motion.

Notes

  • Input images should be under 10 MB (JPEG, PNG, WebP).
  • Video output is typically MP4 format.
  • Generation time varies with duration and resolution — longer clips take more time.

Seedance 2.0 Mini Reference To Video Spicy — Frequently asked questions