Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubGenerates images synchronously based on prompt and resolution. This node connects to the Recraft API to create images from text descriptions with specified dimensions and optional style and control parameters.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
prompt | STRING | Yes | - | Prompt for the image generation. (default: "") |
size | COMBO | Yes | ”1024x1024" "1152x896" "896x1152" "1216x832" "832x1216" "1344x768" "768x1344" "1536x640" "640x1536” | The size of the generated image. (default: “1024x1024”) |
n | INT | Yes | 1-6 | The number of images to generate. (default: 1) |
seed | INT | Yes | 0-18446744073709551615 | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0) |
recraft_style | RECRAFT_STYLE | No | Multiple options available | Optional style selection for image generation. When not provided, defaults to “realistic_image” style. |
negative_prompt | STRING | No | - | An optional text description of undesired elements on an image. (default: "") |
recraft_controls | RECRAFT_CONTROLS | No | Multiple options available | Optional additional controls over the generation via the Recraft Controls node. |
seed parameter only controls when the node re-runs but does not make the image generation deterministic. The actual output images will vary even with the same seed value.
Note: The prompt parameter must be between 1 and 1000 characters in length.
Note: If you use a style_id from the Infinite Style Library, ensure it is not a Vector art style, as this will return SVG data instead of an image and cause an error.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
IMAGE | IMAGE | The generated image(s) as a batched tensor output. When multiple images are generated (n > 1), they are concatenated along the batch dimension. |
Source fingerprint (SHA-256):
946010fbb6a5b99eed11e74de0733f64a270fa62910acf942749c76e0b5448f3