Seedance v1.5 Pro Image-to-Video by BYTEDANCE
bytedance/seedance-v1.5-pro/image-to-videoNative audio-visual joint generation model by ByteDance. Supports unified multimodal generation with precise audio-visual sync, cinematic camera control, and enhanced narrative coherence.
Set up the model and run your first generation.
Ctrl ⏎Examples
Runs published with this model. Load one into the playground and change whatever you like.
Use the provided image as the first frame. On a quiet residential street in a summer afternoon, a young girl in high-quality Japanese anime style slowly walks forward. Her steps are natural and light, with her arms gently swinging in rhythm with her walk. Her body movement remains stable and well-balanced. As she walks, her expression gradually softens into a gentle, warm smile. The corners of her mouth lift slightly, and her eyes look calm and bright. A soft breeze moves her short hair and headband, with individual strands subtly flowing. Her clothes show slight natural motion from the wind. Sunlight comes from the upper side, creating soft highlights and natural shadows on her face and body. Background trees sway gently, and distant clouds drift slowly, enhancing the peaceful summer atmosphere. The camera stays at a medium to medium-close distance, smoothly tracking forward with cinematic motion, stable and controlled. High-quality Japanese hand-drawn animation style, clean linework, warm natural colors, smooth frame rate, consistent character proportions. The mood is calm, youthful, and healing, like a slice-of-life moment from an animated film.
camera_fixed: falseduration: 5generate_audio: trueresolution: 720pseed: -1image: https://static.atlasclou
Providers
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | $0.047 /sec | — | — |
| fal.ai | $1.20 /1M tok | — | — |
| OpenRouter | — | — | — |
| Replicate | — | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.
Seedance v1.5 Pro Text-to-Video$0.235Seedance v1.5 Pro Image-to-Video Fast$0.090Seedance v1.5 Pro Text-to-Video Fast$0.090
Questions
- $0.235 per generation on ElliSekiz — the provider's own price, billed 1:1 from a prepaid USD balance with no markup and no subscription. Failed generations are free.
- Atlas Cloud, fal.ai, OpenRouter, Replicate. Requests route to the cheapest available provider automatically, or you can pin one per request or per model.
- POST to https://ellisekiz.ai/api/v1/generations with "model": "bytedance-seedance-v1-5-pro-image-to-video" and your prompt, authenticated with an ElliSekiz API token. The API tab on this page has the full request for this model, including its own parameters.
- image, aspect_ratio, camera_fixed, duration, generate_audio, last_image, resolution, seed — each one is in the playground form on this page and in the API example.
$0.235 per generation (≈5s clip) · billed 1:1 at provider cost · compare providers