ComfyUI Node
Vertex AI Gemini
A ComfyUI node in AI/Google with 17 inputs and 2 outputs.
Vertex AI Gemini
- image
- image_2
- image_3
- image_4
- image_5
- image_6
- image_7
- image_8
- image_9
- video
- text
- image
◄prompt►
◄api_key►
◄modelgemini-3-pro-image-preview►
◄modeAuto (自动检测)►
◄aspect_ratio1024x1024 (1:1)►
◄temperature0.70►
◄max_tokens2048►
CategoryAI/Google
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | — | |
| api_key | STRING | Vertex AI API Key | |
| model | COMBO | gemini-3-pro-image-preview | 6 options: gemini-2.5-flash, gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview, gemini-3-flash-preview |
| mode | COMBO | Auto (自动检测) | 5 options: Auto (自动检测), Text Generation (纯文本), Image Understanding (图像理解), Image Editing (图像编辑), Video Analysis (视频分析) |
| aspect_ratio | COMBO | 1024x1024 (1:1) | 提示模型生成指定比例的图像 |
| temperature | FLOAT | 0.700–1 | — |
| max_tokens | INT | 20481–8192 | — |
| imageopt | IMAGE | — | |
| image_2opt | IMAGE | — | |
| image_3opt | IMAGE | — | |
| image_4opt | IMAGE | — | |
| image_5opt | IMAGE | — | |
| image_6opt | IMAGE | — | |
| image_7opt | IMAGE | — | |
| image_8opt | IMAGE | — | |
| image_9opt | IMAGE | — | |
| videoopt | IMAGE | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| image | IMAGE | — |