← Back to all generators
lucataco/fuyu-8b
Official
View on Replicate →
Fuyu-8B is a multi-modal text and image transformer trained by Adept AI
Capabilities
Reference Images
Max Tokens
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image * | string (uri) | Input Image | — | — |
prompt * | string | Input prompt | — | — |
max_new_tokens | integer | Max new tokens | 512 | min: 0, max: 2048 |
image required string Input Image
prompt required string Input prompt
max_new_tokens integer Max new tokens
Default:
512 min: 0, max: 2048 Version:
42f23bc87657 Updated: 2/26/2026 14.6K runs
cinemasetfree.com