ComfyUI Node
🔱 Artha Gemini Compose
Describes a character. When no image connected, output is crafted by the parameters. If image input is active, prompt is crafted from the image details. If image input is active and reconstruct is true, prompt is crafted from the image details but parameters override fetched attributes.
🔱 Artha Gemini Compose
- image
- subject
- scene
- camera
- light
- style
- response
- traits
◄text_promptConstruct a prompt describing an image composition in detail.►
◄api_key►
◄modelgemini-2.5-flash►
◄max_tokens5000►
◄temperature0.7►
◄seed0►
◄use_imagefalse►
◄reconstructfalse►
CategoryArtha/LLM/Gemini
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| text_prompt | STRING | Construct a prompt describing an image composition in detail. | — |
| api_key | STRING | API key will be visible in plain text. Consider adding your api to the api.json located inside this custom node folder. | |
| model | COMBO | gemini-2.5-flash | 5 options: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.0-flash, gemini-2.0-flash-lite |
| max_tokens | INT | 50001–8192 | For Gemini models, a token is equivalent to about 4 characters. 100 tokens is equal to about 60–80 English words. |
| temperature | FLOAT | 0.70–2 | A temperature of 0 means only the most likely tokens are selected. Higher values increase randomness. |
| seed | INT | 00–18446744073709550000 | — |
| use_image | BOOLEAN | false | — |
| reconstruct | BOOLEAN | false | — |
| imageopt | IMAGE | — | |
| subjectopt | ARTHASUBJECT | — | |
| sceneopt | ARTHASCENERY | — | |
| cameraopt | ARTHACAM | — | |
| lightopt | ARTHALIGHT | — | |
| styleopt | ARTHASTYLE | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| traits | STRING | — |