ComfyUI Node
Flux 3 Image (API)
A ComfyUI node in Flux3 API with 9 inputs and 2 outputs.
Flux 3 Image (API)
- images
- image
- metadata
◄prompt►
◄aspect_ratioauto►
◄resolution1k►
◄safety_tolerance2►
◄groundingtrue►
◄seed0►
◄timeout_minutes45►
◄api_key►
CategoryFlux3 API
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Describe the image or the edit. Layout: name elements as <id> and end the prompt with a JSON list, bbox = [top, left, bottom, right] on 0-1000. | |
| aspect_ratio | COMBO | auto | auto = aspect ratio of the first reference image, 1:1 without one. |
| resolution | COMBO | 1k | Output size. 4k can take several minutes; the exact size is output_mp in metadata. |
| safety_tolerance | INT | 20–4 | Input and output moderation, 0 = strictest. |
| grounding | BOOLEAN | true | Let the model research the prompt with web and image search before it generates. |
| seed | INT | 00–18446744073709550000 | Not sent (the API has no seed); only makes the node run again. |
| imagesopt | IMAGE | 1-10 reference images (batch), each 256x256 to 16 MP. Refer to them in the prompt as Image 1, 2, ... or <ref_image_0>, ... | |
| timeout_minutesopt | INT | 451–240 | How long the node waits for the result. |
| api_keyopt | STRING | Empty = from .env |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| metadata | STRING | — |