Vidu Contest
WaveSpeed.ai
Beranda/Jelajahi/Seedance Video Models/bytedance/seedance-v1-lite-i2v-720p
image-to-video

image-to-video

Seedance Lite I2V 720P

bytedance/seedance-v1-lite-i2v-720p

ByteDance Seedance Lite i2v 720p creates coherent multi-shot image-to-video clips with smooth, stable motion and prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

Hint: You can drag and drop a file or click to upload

preview

Hint: You can drag and drop a file or click to upload

Whether to fix the camera position.

Idle

Permintaan Anda akan membutuhkan $0.16 per run.

Untuk $10 Anda dapat menjalankan model ini sekitar 62 kali.

Satu lagi hal:

ContohLihat semua

README

Seedance v1 Lite I2V 720p — bytedance/seedance-v1-lite-i2v-720p

Seedance v1 Lite I2V 720p generates short videos from a single reference image plus a motion-focused prompt. Upload a starting image, describe what happens (subject action + camera behavior), and the model animates the scene while keeping the input image as the visual anchor. You can also provide an optional last_image to better control how the clip ends.

Key capabilities

  • Image-to-video generation anchored to a reference image (720p output)
  • Optional last_image for smoother ending continuity and better narrative “landing”
  • Prompt-controlled motion (character actions, environmental effects, camera beats)
  • Optional camera_fixed mode when you want motion without camera movement

Use cases

  • Character animation from a single keyframe (actions, expressions, subtle body motion)
  • Short story beats for trailers, storyboards, and concept previews
  • Product or object animation with controlled motion and stable framing
  • Start-to-end guided shots using last_image for more predictable outcomes

Pricing

DurationPrice per video
5s$0.16
10s$0.32
15s$0.48
20s$0.64

Inputs

  • image (required): starting reference image (first-frame anchor)
  • prompt (required): motion and scene direction
  • last_image (optional): end-frame reference to guide the finishing state

Parameters

  • prompt: describes subject action, environment motion, and camera direction
  • image: input image (upload or URL)
  • last_image: optional end reference image (upload or URL)
  • duration: video length in seconds
  • aspect_ratio: output aspect ratio selection
  • camera_fixed: whether to lock the camera position
  • seed: random seed (-1 for random; fixed value for reproducible results)
  • safety checker: enabled filtering for safer generations (if available in your UI)

Prompting guide (I2V)

Write prompts like a director’s beat sheet:

  • Subject action: what changes over time (stands up, looks around, runs forward, picks up an item)
  • Camera: close-up, push-in, follow, orbit, rack focus (or keep it fixed)
  • Environment: wind, fog, particles, light effects, background motion
  • Continuity: explicitly say what must remain consistent (identity, colors, scene layout)

Example prompts

  • A fox stands up and looks around, then runs forward and finds a glowing gem. Close-up of the fox picking up the jewel, cinematic lighting, gentle snow particles, smooth motion.
  • A hero product on a table. Slow push-in, subtle highlight movement across the surface, light dust motes, clean studio look, camera_fixed enabled.
  • A character turns toward the camera and smiles. Hair sways lightly in the wind, warm sunset backlight, shallow depth of field, natural motion.