README.md

metadata

title: qwenprep
emoji: 🚃
colorFrom: purple
colorTo: gray
sdk: gradio
sdk_version: 6.26.0
app_file: app.py
python_version: 3.12
pinned: false
suggested_hardware: zero-a10g
models:
  - prithivMLmods/Qwen-Image-Edit-Rapid-AIO-V19
  - Qwen/Qwen-Image-Edit-2511
  - Qwen/Qwen2.5-VL-7B-Instruct
packages:
  - ffmpeg
short_description: tags and generates training variations

Dining Cart

Private, shared dataset preparation for Caboose and related Qwen, WAN, and Stable Diffusion trainers. It extracts video frames, batches Qwen Image edits, and writes Qwen-native or Stable Diffusion captions into a single bucket mounted at /data.