ComfyUI Node
PD: Gemini Image (ComfyUI AuthToken)
A ComfyUI node in PD_Tools/Image_Generation with 9 inputs and 2 outputs.
PD: Gemini Image (ComfyUI AuthToken)
- images
- files
- image
- info
◄auth_token►
◄promptA futuristic city with flying cars►
◄modelgemini-2.5-flash-image►
◄aspect_ratioauto►
◄resolution1K►
◄seed0►
◄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 (9)
| Name | Type | Default | Description |
|---|---|---|---|
| auth_token | STRING | — | |
| prompt | STRING | A futuristic city with flying cars | Describe what you want to generate |
| model | COMBO | gemini-2.5-flash-image | 2 options: gemini-2.5-flash-image, gemini-2.5-flash-image-preview |
| aspect_ratio | COMBO | auto | 8 options: auto, 1:1, 16:9, 9:16, 4:3, 3:4, +2 |
| resolution | COMBO | 1K | 4 options: auto, 1K, 2K, 4K |
| seed | INT | 00–18446744073709550000 | — |
| imagesopt | IMAGE | Reference image(s) for image-to-image generation | |
| 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. | Optional system instructions |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| info | STRING | — |