Dataset Viewer
Auto-converted to Parquet
video_url
stringclasses
2 values
conversation
listlengths
2
2
num_frames
int64
5
5
https://huggingface.co/datasets/diffusion-datasets/sample-videos/resolve/main/sample2.mp4
[ { "content": [ { "text": "Can you describe what is happening?", "type": "text" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" } ], "role": "user" }, { "content": [ { "text": "A cat is present in the scene.", "type": "text" } ], "role": "assistant" } ]
5
https://huggingface.co/datasets/diffusion-datasets/sample-videos/resolve/main/sample1.mp4
[ { "content": [ { "text": "What is in this video?", "type": "text" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" }, { "text": null, "type": "image" } ], "role": "user" }, { "content": [ { "text": "There is a cat in the video.", "type": "text" } ], "role": "assistant" } ]
5

eagle0504/llava-video-text-dataset

This is a tiny LLaVA dataset with exactly four video samples for training.

  • Field video_url: Video URLs (MP4/GIF format)
  • Field conversation: LLaVA conversation format with user/assistant roles
  • Field num_frames: Number of frames per video (5)

Dataset Structure

Each sample contains a conversation in LLaVA format:

{
  "video_url": "https://example.com/video.mp4",
  "conversation": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this video?"},
        {"type": "image"},
        {"type": "image"},
        {"type": "image"},
        {"type": "image"},
        {"type": "image"}
      ]
    },
    {
      "role": "assistant", 
      "content": [{"type": "text", "text": "There is a cat in the video."}]
    }
  ],
  "num_frames": 5
}

Usage

from datasets import load_dataset

dataset = load_dataset("eagle0504/llava-video-text-dataset")

Model Compatibility

This dataset is designed for LLaVA models that support video input through multiple image frames.

Downloads last month
16