aodianyun/qwen2-vl-2b 🖼️🔢📝 → 📝

▶️ 130 runs 📅 Sep 2024 ⚙️ Cog 0.9.20

About

Example Output

Prompt:

"Describe the video."

Output

The video is about a training session on derivative classification, which seems to be an event or seminar related to financial markets and derivatives trading. The woman in the video appears to be giving a presentation or lecture, possibly explaining the concepts of derivative classification in a structured manner. The setting suggests that this might be part of a larger conference or workshop focused on finance and investment strategies.

Performance Metrics

5.49s Prediction Time

111.90s Total Time

All Input Parameters

{
  "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
  "width": 128,
  "height": 128,
  "prompt": "Describe the video.",
  "max_tokens": 128,
  "temperature": 0.7,
  "max_duration": 60,
  "repetition_penalty": 1.1
}

Input Parameters

video (required) Type: string: Video to process
width Type: integerDefault: 128Range: 128 - 2048: Width for the video
height Type: integerDefault: 128Range: 128 - 2048: Height for the video
prompt Type: stringDefault: Describe the video.: Prompt to use for the video
max_tokens Type: integerDefault: 128Range: 1 - 8192: Maximum number of tokens to generate
temperature Type: numberDefault: 0.7Range: 0.01 - 1: Temperature for the model (0.7 is a good default).
max_duration Type: numberDefault: 60Range: 1 - 768: Maximum duration of the video in seconds (above 360, may run out of VRAM).
repetition_penalty Type: numberDefault: 1.1Range: 0.01 - 1.5: Repetition penalty for the model (1.1 is a good default).

Output Schema

Output

Type: string

Version Details

Version ID: 6cc44731e30e71024f61dca89f33f95b0ef81854051eb85fd340c26b0871d086
Version Created: September 7, 2024

Run on Replicate →