ComfyUI Node
vergora 文生图（gpt-image）
A ComfyUI node in vergora with 12 inputs and 3 outputs.
vergora 文生图（gpt-image）
- image
- image_path
- image_url
◄prompt►
◄modelgpt-image-2►
◄size1024x1024►
◄extra_json►
◄model_override►
◄qualityauto►
◄backgroundauto►
◄output_formatauto►
◄output_compression0►
◄moderationauto►
◄n1►
◄user►
Categoryvergora
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | — | |
| model | COMBO | gpt-image-2 | 3 options: gpt-image-2, gpt-image-2.5-flare, gpt-image-2.5-sunburst |
| size | COMBO | 1024x1024 | auto omits the field; the upstream answers 1024x1024 with 1254x1254 |
| extra_jsonopt | STRING | Extra request fields, e.g. {"size": "1536x1024"} | |
| model_overrideopt | STRING | Any other model id, wins over the dropdown | |
| qualityopt | COMBO | auto | Official quality field; auto = do not send it |
| backgroundopt | COMBO | auto | auto / transparent / opaque |
| output_formatopt | COMBO | auto | auto / png / jpeg / webp |
| output_compressionopt | INT | 00–100 | 0-100, only sent for jpeg/webp (0 = do not send it) |
| moderationopt | COMBO | auto | auto / low |
| nopt | INT | 11–10 | How many pictures to ask for; the gateway returned a single one in our tests |
| useropt | STRING | Official abuse-tracking field, sent when you fill it in |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| image_path | STRING | — |
| image_url | STRING | — |