ComfyUI Node
Groq Vision
A ComfyUI node in groq/vision with 8 inputs and 2 outputs.
Groq Vision
- image
- text
- usage_info
◄promptWhat is in this image?►
◄modelmeta-llama/llama-4-scout-17b-16e-instruct►
◄temperature1.0►
◄max_tokens1024►
◄api_key►
◄system_prompt►
◄jpeg_quality95►
Categorygroq/vision
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| prompt | STRING | What is in this image? | — |
| model | COMBO | meta-llama/llama-4-scout-17b-16e-instruct | 2 options: meta-llama/llama-4-scout-17b-16e-instruct, meta-llama/llama-4-maverick-17b-128e-instruct |
| temperature | FLOAT | 1.00–2 | — |
| max_tokens | INT | 10241–8192 | — |
| api_keyopt | STRING | — | |
| system_promptopt | STRING | — | |
| jpeg_qualityopt | INT | 9550–100 | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| usage_info | STRING | — |