ComfyUI Node
Seedance 文生视频 (Text to Video)
A ComfyUI node in Seedance with 9 inputs and 4 outputs.
Seedance 文生视频 (Text to Video)
- api_config
- video
- video_url
- task_id
- response
◄modelseedance-2.0-standard-t2v►
◄prompt►
◄seconds5►
◄resolution720p►
◄ratioadaptive►
◄generate_audiotrue►
◄seed-1►
◄skip_errorfalse►
CategorySeedance
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | seedance-2.0-standard-t2v | standard/fast/mini = quality tiers; 'global-' models run on overseas infrastructure. | standard/fast/mini 为档位，带 global- 的为海外版通道。 |
| prompt | STRING | Text prompt, up to 20480 chars. In multimodal mode you can reference materials as @Image 1 / @Video 1 / @Audio 1. | 文本提示词，多模态可用 @Image 1、@Video 1 指代第几个素材。 | |
| seconds | COMBO | 5 | Video duration in seconds; -1 lets the model decide. | 视频时长（秒），-1 表示模型智能选择。 |
| resolution | COMBO | 720p | 1080p/2k/4k are upscaled output tiers; native1080p/native4k are Standard-tier only. | 1080p/2k/4k 为超分输出档，native 档仅 Standard 模型支持。 |
| ratio | COMBO | adaptive | Aspect ratio; adaptive follows the input material. | 画面比例，adaptive 为自适应。 |
| generate_audioopt | BOOLEAN | true | Generate voice-over / sound effects. | 是否生成配音与音效。 |
| seedopt | INT | -1-1–2147483647 | -1 = random seed. | -1 表示随机种子。 Fixed reuses the cached result while all inputs stay unchanged; randomize/increment/decrement starts a new execution. | Fixed 在输入不变时复用缓存；随机、递增或递减会触发新任务。 |
| api_configopt | SEEDANCE_CONFIG | Connect a 'Seedance API Config' node; falls back to SEEDANCE_API_KEY env var. | |
| skip_erroropt | BOOLEAN | false | On failure return a placeholder error video instead of stopping the workflow. | 失败时输出占位错误视频而不中断工作流。 |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |
| task_id | STRING | — |
| response | STRING | — |