ComfyUI Node
Seedream / Dola Seedream v5 Pro 图层拆分（2 合 1）
A ComfyUI node in Seedance with 8 inputs and 6 outputs.
Seedream / Dola Seedream v5 Pro 图层拆分（2 合 1）
- image
- api_config
- images
- masks
- image_urls
- image_count
- task_id
- response
◄prompt►
◄resolutionauto►
◄output_formatpng►
◄skip_errorfalse►
◄seed0►
◄modelseedream-v5-pro-layer-decomposition►
CategorySeedance
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Exactly one source image, up to 30 MB after upload. | 必须连接 1 张待拆分图片，上传后不超过 30 MB。 | |
| prompt | STRING | Optional decomposition instruction, up to 2000 characters. | 可选拆分要求，最多 2000 字符。 | |
| resolution | COMBO | auto | Layer decomposition resolution: auto, 1k, 1.5k, or 2k. | 图层拆分分辨率：auto、1k、1.5k 或 2k。 |
| output_format | COMBO | png | PNG is recommended because generated layers may contain transparency. | 建议使用 PNG，生成图层可能包含透明通道。 |
| api_configopt | SEEDANCE_CONFIG | Connect Seedance API Config; otherwise SEEDANCE_API_KEY is used. | |
| skip_erroropt | BOOLEAN | false | On failure return placeholder image/mask lists instead of stopping the workflow. | 失败时输出占位图片与蒙版列表而不中断工作流。 |
| seedopt | INT | 00–18446744073709550000 | ComfyUI cache seed only; this value is not sent to Seedream. | 仅用于 ComfyUI 缓存，不会发送给 Seedream。 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。 |
| modelopt | COMBO | seedream-v5-pro-layer-decomposition | Domestic Seedream or overseas Dola Seedream layer decomposition. | 选择国内 Seedream 或海外 Dola Seedream 图层拆分模型。 |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| masks | MASK | — |
| image_urls | STRING | — |
| image_count | INT | — |
| task_id | STRING | — |
| response | STRING | — |