Seedance·de ByteDanceText to video
Seedance 2.0 Text-to-Video
Generate high-quality videos from text with ByteDance Seedance 2.0. Supports synchronized audio generation, 480p-720p resolution, 4-15 second duration, and various aspect ratios including ultrawide 21:9. ⚠️ Important: This model cannot process images containing likenesses of real people. Use only illustrations, drawings, or AI-generated characters.
bytedance/seedance-2.0/text-to-videoParámetros
| Parámetro | Tipo | Por defecto | Rango u opciones |
|---|---|---|---|
duration durationVideo duration in seconds (4-15), or -1 for model to choose automatically. | select | 5 | -1, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 |
resolution resolutionVideo resolution. | select | 720p | 480p, 720p, 720p-SR, 1080p, 1080p-SR, 1440p-SR, 4k |
generate audio generate_audioWhether to generate synchronized audio (voice, sound effects, background music). | select | true | true, false |
ratio ratioAspect ratio. 'adaptive' automatically selects based on prompt context. | select | adaptive | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive |
return last frame return_last_frameWhether to return the last frame as a separate image. | select | false | true, false |
watermark watermarkWhether to add a watermark. | select | false | true, false |
Entradas
Sin archivos de referencia: este modelo trabaja solo con el prompt.
Guía de prompts para Seedance
Notas
- Seedance has no negative_prompt — phrase exclusions as positive constraint phrases at the tail (e.g. “do not generate a watermark”, “keep it subtitle-free”).
- There is no negative prompt on this family; write exclusions as positive constraints.
- Weight syntax such as (word:1.3) is ignored; it only wastes prompt space.
- Keep to at most 4 distinct characters in one prompt.
De las reglas verificadas de LUVI para esta familia.