You're looking at a specific version of this model. Jump to the model overview.

cuuupid /qwen2-vl-2b:d312c2be

Input

string
Shift + Return to add a new line

Prompt to use for the video

Default: "Describe the video."

*file

Video to describe

integer
(minimum: 128, maximum: 2048)

Width for the video

Default: 360

integer
(minimum: 128, maximum: 2048)

Height for the video

Default: 360

number

Maximum duration of the video in seconds (above 30, may run out of VRAM).

Default: 60

integer

Maximum number of tokens to generate

Default: 128

number

Temperature for the model (0.7 is a good default).

Default: 0.7

Output

[ "The video features a woman standing behind a podium, speaking to the camera. She is wearing a blue shirt and appears to be giving a presentation or lecture. The woman's facial expression suggests that she is engaged and passionate about the topic she is discussing. The background of the video is not visible, but it can be assumed that it is an indoor setting, possibly a conference room or lecture hall. The woman's speech is not audible, but her body language and gestures suggest that she is using hand movements to emphasize certain points. Overall, the video seems to be a formal presentation or lecture, with the woman as the main speaker." ]
Generated in