ComfyUI Node
🔱 Gemini Light
Light settings for image or video prompting.If use image is selected the setting are fetched from the uploaded image by Gemini Vision.
🔱 Gemini Light
- light
- markdown
◄sourceNONE►
◄qualityNONE►
◄directionNONE►
◄timeofdayNONE►
◄phenomenaNONE►
◄api_key►
◄modelgemini-2.5-flash►
◄max_tokens5000►
◄temperature0.7►
◄randomizefalse►
◄use_imagefalse►
◄image▾►
CategoryArtha/LLM/GEMINI
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| source | COMBO | NONE | 14 options: NONE, DAYLIGHT, SUNNY LIGHT, MOON LIGHT, OVERCAST LIGHT, SUNRISE LIGHT, +8 |
| quality | COMBO | NONE | 5 options: NONE, SOFT LIGHT, HARD LIGHT, LOW CONTRAST LIGHT, HIGH CONTRAST LIGHT |
| direction | COMBO | NONE | 7 options: NONE, TOP LIGHT, SIDE LIGHT, BACK LIGHT, RIM LIGHT, BOTTOM LIGHT, +1 |
| timeofday | COMBO | NONE | 7 options: NONE, DAYTIME LIGHT, NIGHT LIGHT, DAWN LIGHT, SUNRISE LIGHT, DUSK LIGHT, +1 |
| phenomena | COMBO | NONE | 17 options: NONE, LENS FLARE, GOD RAYS, VOLUMETRIC LIGHT, CAUSTICS, REFLECTION, +11 |
| 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, and there's no randomness. Conversely, a high temperature injects a high degree of randomness into the tokens selected by the model, leading to more unexpected, surprising model responses. |
| randomize | BOOLEAN | false | — |
| use_image | BOOLEAN | false | — |
| image | COMBO | 1 options: example.png |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| light | ARTHALIGHT | — |
| markdown | STRING | — |