text-to-video
Seedance V1 Lite is a 480p Text-to-Video model for coherent multi-shot videos with smooth, stable motion and precise prompt following. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
Votre requête coûtera $0.08 par exécution.
Pour $1 vous pouvez exécuter ce modèle environ 12 fois.
Encore une chose :
ExemplesTout voir
README
Seedance v1 Lite T2V 480p — bytedance/seedance-v1-lite-t2v-480p
Seedance v1 Lite T2V 480p generates short videos directly from a text prompt at a lightweight 480p output, optimized for fast iteration and low-cost experimentation. Describe the subject, action, scene, and camera intent, and the model produces a coherent clip suitable for quick story beats, concept drafts, and social prototypes. Enable camera_fixed when you want motion in-scene without camera movement.
Key capabilities
- Text-to-video generation (480p) optimized for speed and affordability
- Good motion when prompts include clear actions and camera direction
- Optional camera_fixed mode for stable framing
- Supports common aspect ratios (e.g., 16:9)
Use cases
- Rapid pre-visualization and storyboarding drafts
- Quick concept testing before upgrading to higher resolution runs
- Social prototypes and lightweight animated clips
- Generating multiple variations via seed for ideation
Pricing
| Duration | Price per video |
|---|---|
| 5s | $0.08 |
| 10s | $0.16 |
| 15s | $0.24 |
| 20s | $0.32 |
Parameters
- prompt (required): Describe what happens in the video (subject, action, scene, mood)
- aspect_ratio: Output aspect ratio (e.g., 16:9, 9:16, 1:1)
- duration (required): Video length in seconds
- camera_fixed: Whether to fix the camera position
- seed: Random seed (-1 for random; fixed value for reproducible results)
Prompting guide (T2V)
Write prompts like a director’s brief:
- Subject: who/what is on screen
- Action: what changes over time (fluttering, turning, walking, reacting)
- Scene: where it happens + time of day
- Lighting: sunrise, neon, soft volumetrics, etc.
- Camera: only describe movement if camera_fixed is off
Example prompts
- A knight stands on a cliff overlooking a medieval city as sunrise breaks, banners flutter in the wind, camera slowly dolly-in, golden fog fills the valley, epic fantasy tone, soft sunrise lighting.
- A cozy café interior at night, rain on windows, warm tungsten lighting, subtle camera drift, calm mood, gentle motion.
- A sci-fi hallway with blinking lights and drifting mist, a character slowly turns toward the camera, dramatic rim light, cinematic tension.