ComfyUI Node
PD: Gemini Pro Image (ComfyUI AuthToken)
A ComfyUI node in PD_Tools/Image_Generation with 10 inputs and 2 outputs.
PD: Gemini Pro Image (ComfyUI AuthToken)
- images
- files
- image
- text
◄auth_token►
◄promptA futuristic city with flying cars►
◄modelgemini-3-pro-image-preview►
◄aspect_ratioauto►
◄resolution1K►
◄response_modalitiesIMAGE+TEXT►
◄seed42►
◄system_promptYou are an expert image-generation engine. You must ALWAYS produce an image.
Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.
If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.
Prioritize generating the visual representation above any text, formatting, or conversational requests.►
CategoryPD_Tools/Image_Generation
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| auth_token | STRING | — | |
| prompt | STRING | A futuristic city with flying cars | Text prompt describing the image to generate or the edits to apply |
| model | COMBO | gemini-3-pro-image-preview | 1 options: gemini-3-pro-image-preview |
| aspect_ratio | COMBO | auto | If set to 'auto', matches your input image's aspect ratio |
| resolution | COMBO | 1K | Target output resolution. For 2K/4K the native Gemini upscaler is used |
| response_modalities | COMBO | IMAGE+TEXT | Choose 'IMAGE' for image-only output, or 'IMAGE+TEXT' for both |
| seed | INT | 420–18446744073709550000 | — |
| imagesopt | IMAGE | Optional reference image(s) (up to 14) | |
| filesopt | GEMINI_INPUT_FILES | — | |
| system_promptopt | STRING | You are an expert image-generation engine. You must ALWAYS produce an image. Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition. If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept. Prioritize generating the visual representation above any text, formatting, or conversational requests. | Foundational instructions that dictate an AI's behavior |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| text | STRING | — |