# ByteDance Seedream 4.5 & 5.0 (Legacy)

This node generates or edits images using ByteDance's Seedream models (versions 4.0, 4.5, 5.0 Lite, and 5.0 Pro). It provides unified text-to-image generation and precise single-sentence image editing at up to 4K resolution. This is the legacy (V2) version of the Seedream node.

## Inputs

### Common Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `model` | The Seedream model version to use for generation. Each model has different capabilities and pricing. | DYNAMIC_COMBO | Yes | `"seedream 5.0 pro"`<br>`"seedream 5.0 lite"`<br>`"seedream-4-5-251128"`<br>`"seedream-4-0-250828"` |
| `prompt` | Text prompt for creating or editing an image (default: empty string). | STRING | Yes | N/A |
| `seed` | Seed to use for generation (default: 0). | INT | Yes | 0 to 2147483647 |
| `watermark` | Whether to add an "AI generated" watermark to the image (default: False). | BOOLEAN | Yes | True / False |
| `thinking` | Enable the model's prompt-optimization reasoning ('thinking') for better adherence. Can substantially increase generation time — notably on Seedream 5.0 Pro. Can only be disabled for text-to-image (not when reference images are provided) (default: True). | BOOLEAN | No | True / False |

### `seedream 5.0 pro` Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. | COMBO | Yes | Multiple model-specific presets available, includes `Custom` |
| `width` | Custom width for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 3136 (step 2) |
| `height` | Custom height for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 2496 (step 2) |

### `seedream 5.0 lite` Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. | COMBO | Yes | Multiple model-specific presets available, includes `Custom` |
| `width` | Custom width for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 6240 (step 2) |
| `height` | Custom height for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 4992 (step 2) |
| `max_images` | Maximum number of images to generate. With 1, exactly one image is produced. With >1, the model generates between 1 and max_images related images (e.g., story scenes, character variations). Total images (input + generated) cannot exceed 15. (default: 1) | INT | Yes | 1 to 14 |
| `fail_on_partial` | If enabled, abort execution if any requested images are missing or return an error. (default: False) | BOOLEAN | Yes | True / False |

### `seedream-4-5-251128` Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. | COMBO | Yes | Multiple model-specific presets available, includes `Custom` |
| `width` | Custom width for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 6240 (step 2) |
| `height` | Custom height for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 4992 (step 2) |
| `max_images` | Maximum number of images to generate. With 1, exactly one image is produced. With >1, the model generates between 1 and max_images related images (e.g., story scenes, character variations). Total images (input + generated) cannot exceed 15. (default: 1) | INT | Yes | 1 to 10 |
| `fail_on_partial` | If enabled, abort execution if any requested images are missing or return an error. (default: False) | BOOLEAN | Yes | True / False |

### `seedream-4-0-250828` Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. | COMBO | Yes | Multiple model-specific presets available, includes `Custom` |
| `width` | Custom width for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 6240 (step 2) |
| `height` | Custom height for image. Value is working only if `size_preset` is set to `Custom` (default: 2048). | INT | Yes | 1024 to 4992 (step 2) |
| `max_images` | Maximum number of images to generate. With 1, exactly one image is produced. With >1, the model generates between 1 and max_images related images (e.g., story scenes, character variations). Total images (input + generated) cannot exceed 15. (default: 1) | INT | Yes | 1 to 10 |
| `fail_on_partial` | If enabled, abort execution if any requested images are missing or return an error. (default: False) | BOOLEAN | Yes | True / False |

### Reference Inputs

| Parameter | Description | Data Type | Required | Range |
|-----------|-------------|-----------|----------|-------|
| `images` | Growable slot: connect 1..N items (e.g. `image_1`, `image_2`, ...); the count limit depends on the selected model (see model sections). Optional reference image(s) for image-to-image or multi-reference generation. With no reference images, the node works in text-to-image mode. | IMAGE | No | 0 to 10 images (`seedream 5.0 pro`, `seedream-4-5-251128`, `seedream-4-0-250828`)<br>0 to 14 images (`seedream 5.0 lite`) |

### Notes on constraints

- `width` and `height` only take effect when `size_preset` is set to `Custom`.
- The total number of reference images plus generated images cannot exceed 15.
- `thinking` can only be disabled for text-to-image generation, not when reference images are provided.
- Seedream 5.0 Pro does not support batch generation: it always produces a single image, so `max_images` and `fail_on_partial` are not available for this model.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `image` | The generated or edited image as a tensor. If multiple images were requested, they are concatenated into a single batch. | IMAGE |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNodeV2/en.md)

---
**Source fingerprint (SHA-256):** `f1a84171d94c602ec5417e43857ddf511ab1e54caa089b1928f740d3a38423f8`
