← Back to all generators
lucataco/qwen2-vl-7b-instruct
OfficialView on Replicate →
Latest model in the Qwen family for chatting with video and image models
Capabilities
Max Tokens
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
media* | string(uri) | Input image or video file | — | — |
max_new_tokens | integer | Maximum number of tokens to generate | 128 | min: 1, max: 512 |
prompt | string | Custom prompt to guide the description | "Describe this in detail." | — |
mediarequiredstringInput image or video file
max_new_tokensintegerMaximum number of tokens to generate
Default:
128min: 1, max: 512promptstringCustom prompt to guide the description
Default:
"Describe this in detail."Version:
bf57361c7567Updated: 7/25/2026365.2K runs
cinemasetfree.com