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

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.

image-to-video$0.7600/ run

Prompt

0/2000

Image

PreviewJSON

Your result will appear here

Upload an image, write a prompt and hit Generate.

Examples

Low-angle wide shot, athletic blonde woman with low side braid, toned glistening abs covered in sweat, white sport sunglasses reflecting blue sky, thick white sweat wristbands on both wrists. Dynamic slow subtle movement, vintage Kodak Gold 200 film texture, crisp 4K 60fps, bright clean sport fashion aesthetic.

Wide-angle first-person selfie skydiving footage, tandem pair leaping out of skydiving plane, clear blue sky, sea of clouds and snow-capped alpine mountains; dynamic smooth camera, subtle handheld shake to simulate free fall, bright harsh midday sunlight, 4K 60fps cinematic travel adventure clip.

Wide-angle first-person selfie skydiving footage, tandem pair leaping out of skydiving plane, clear blue sky, sea of clouds and snow-capped alpine mountains; dynamic smooth camera, subtle handheld shake to simulate free fall, bright harsh midday sunlight, 4K 60fps cinematic travel adventure clip.

Related models

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 / image-to-video-spicy15% OFFimage-to-video
seedance-2.0 / image-to-video-spicy

Seedance 2.0 Spicy Image to Video is a fast AI image-to-video generation model that creates high-quality cinematic clips from images, optimized for scalable content generation with smooth animations and stable aesthetics. Ready-to-use REST inference API for animating images, social media clips, product videos, advertising creatives, visual storytelling, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.

Seedance$0.5100$0.6000

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.

Key Features

  • Native 30-second clips — up to 6x the duration ceiling of Seedance 2.0, with room for multi-beat scenes in a single generation.
  • Up to 50 full-modal reference assets — the richest reference budget in the Seedance family for complex multi-character, multi-scene compositions.
  • Image-faithful generation — preserves the reference image's subject identity, composition and lighting while animating it into natural motion.
  • Native audio-visual synchronization — generates video with synchronized audio in a single pass (enabled by default).
  • Sharper editing and generation control — ByteDance's next-generation Seed architecture improves precision over Seedance 2.0 in both prompt adherence and reference fidelity.
  • Director-level control over camera movement, lighting, shadows and character performance through prompts.

Parameters

ParameterRequiredDescription
promptYesDetailed description of the cinematic scene and desired motion.
imageYesStart image URL to guide the video generation.
last_imageNoLast frame image URL for video continuation.
durationNoVideo length in seconds: 4-30 (default: 5).
aspect_ratioNoOutput format: 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 (default: 16:9).
resolutionNoOutput resolution: 480p, 720p (default), or 1080p.
bitrate_modeNoBitrate quality: standard (default) or high.
generate_audioNoGenerate synchronized audio (default: true).

How to Use

  1. Upload a start image to guide the video generation.
  2. Write your prompt — describe the scene with cinematic detail: action, camera movement, lighting, mood.
  3. Set duration — choose any duration from 4 to 30 seconds.
  4. Run — submit and download your cinematic video with synchronized audio.

Code Examples

import os
import requests

response = requests.post(
    "https://aircube.ai/api/v3/seedance-2.5/image-to-video",
    headers={
        "Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
    "prompt": "A woman slowly turns her head and smiles, soft golden hour lighting, cinematic depth of field",
    "image": "https://example.com/portrait.jpg",
    "duration": 5,
    "resolution": "1080p",
    "generate_audio": true
},
    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$0.76
480p5s$0.95
480p6s$1.14
480p8s$1.52
480p10s$1.90
480p12s$2.28
480p15s$2.85
480p20s$3.80
480p25s$4.75
480p30s$5.70
720p4s$1.76
720p5s$2.20
720p6s$2.64
720p8s$3.52
720p10s$4.40
720p12s$5.28
720p15s$6.60
720p20s$8.80
720p25s$11.00
720p30s$13.20
1080p4s$4.20
1080p5s$5.25
1080p6s$6.30
1080p8s$8.40
1080p10s$10.50
1080p12s$12.60
1080p15s$15.75
1080p20s$21.00
1080p25s$26.25
1080p30s$31.50

Billing rules

  • 480p / 4s: $0.76.
  • 720p / 4s: $1.76.
  • 1080p / 4s: $4.20.
  • Longer durations scale proportionally.
  • Failed generations are not charged.

Best Use Cases

  • Product demos — animate product shots into cinematic, multi-beat showcase videos.
  • Commercials — create longer-form professional ad content from reference imagery.
  • Character animation — animate characters or artwork into full cinematic footage.
  • Scene extension — transform a single keyframe into a full 30-second cinematic sequence.
  • Style-consistent series — use reference images to maintain visual consistency across multiple clips.

Pro Tips

  • Upload high-quality reference images for the best subject preservation.
  • Write prompts like a film director — include lighting, camera angles and mood.
  • Use the extended 30-second ceiling for scenes with more than one narrative beat.
  • Start with a short duration (4-5s) to iterate, then extend up to 30s for the final cut.
  • Describe character expressions and actions for more engaging scenes.

Notes

  • Native audio generation is included by default — videos come with synchronized sound.
  • Duration range: 4-30 seconds (continuous).
  • Supports up to 1080p output resolution.
  • Successor to Seedance 2.0 with a longer duration ceiling and richer reference support.

Seedance 2.5 Image To Video — Frequently asked questions