Skip to content

Conversation

adrianboguszewski
Copy link
Contributor

No description provided.

ezelanza and others added 30 commits July 24, 2025 12:16
…--num_frames) for non-interactive captioning
ezelanza and others added 4 commits September 8, 2025 09:50
- Add comprehensive file checking for LLaVA video models
- Check for critical model files (openvino_model.xml, openvino_model.bin, config.json, etc.)
- Trigger re-download if any essential files are missing
- Improve user feedback with detailed console messages
- Ensure robust model loading by validating all required components
- Fixed generate_caption_video function parameters and logic
- Improved frame processing and video array handling
- Updated function calls to match new signature
- Cleaned up model loading return values
@ezelanza ezelanza force-pushed the video-captioning-demo-llava branch from 46f36fc to b2df3c9 Compare September 28, 2025 15:23
@ezelanza ezelanza force-pushed the video-captioning-demo-llava branch from b2df3c9 to cb010f7 Compare September 28, 2025 15:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants