ComfyUI Node
Relay Image
Generates or edits images through a relay: OpenAI image API, Seedream-style API, images through chat, or native Gemini.
Relay Image
- images
- image
- text
◄relay▾►
◄model►
◄prompt►
◄api_format▾►
◄seed0►
◄extra_json►
◄timeout300►
CategoryAPI Relay
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| relay | COMBO | Add relays in the Relay Manager window (tools/start_manager in the plugin folder). After editing relays.json by hand, press R to refresh. | |
| model | STRING | Model name on the relay. The Relay Models node lists them | |
| prompt | STRING | — | |
| api_format | COMBO | images: OpenAI image API (gpt-image, dall-e, flux...). Uses /v1/images/edits when there are reference images images-json: sends reference images in the image field to /v1/images/generations (Seedream, Jimeng...) chat: gets the image through the chat API (nano-banana on most relays) gemini: native Gemini /v1beta API (nano-banana, with aspect ratio and 4K options) | |
| seed | INT | 00–4294967295 | Not sent to the API. It only decides whether to call again: a new value makes a new (billed) call, the same value reuses the last result |
| extra_json | STRING | JSON object merged into the request body, such as {"quality": "high"}. Use null to remove a field | |
| timeout | INT | 30010–7200 | — |
| imagesopt | IMAGE | Optional. Every image in the batch is sent as a reference image |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| text | STRING | — |