cinemasetfree.com
← Back to all generators
lucataco/llama-3-vision-alpha
Official
View on Replicate →
Projection module trained to add vision capabilties to Llama 3 using SigLIP
Capabilities
Reference Images
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image * | string (uri) | Input image | — | — |
prompt | string | Input prompt | "Describe the image" | — |
image required string Input image
prompt string Input prompt
Default:
"Describe the image" Version:
79f9f3418f65 Updated: 2/26/2026 6.8K runs