Prince Canuma
ea063f7550
Cast LM weights to bfloat16
2026-01-13 23:30:26 +01:00
Prince Canuma
fc6ef20c1b
Add custom text encoder with quantization
...
Co-authored-by: HimanshU Mourya <40685364+codingstark-dev@users.noreply.github.com >
2026-01-13 22:56:51 +01:00
Prince Canuma
01d895bc77
Add frame number validation in video generation and update Gemma3 text encoder to use validated mlx-vlm implementation
2026-01-13 17:12:11 +01:00
Prince Canuma
4f6fc8252c
Add example usage to README and enhance console output in generate.py with ANSI colors
2026-01-12 16:45:09 +01:00
Prince Canuma
28d03d8846
setup
2026-01-12 16:17:45 +01:00
Prince Canuma
7eac6ae7de
Replace imageio with OpenCV for video saving in generate.py; updated default frame count to 100.
2026-01-12 16:12:41 +01:00
Prince Canuma
666e1f2e0c
Refactor model path handling: moved get_model_path function to utils.py and updated generate.py to use the new import.
2026-01-12 15:54:32 +01:00
Prince Canuma
75511a0b17
Remove main.py and refactor video generation logic into generate.py.
2026-01-12 14:23:02 +01:00
Prince Canuma
7114b023bd
- Refactor video generation script
...
- Introduced argparse for parameter handling, streamlined model loading, and enhanced denoising functions.
- Updated VAE weight sanitization for compatibility and improved activation function handling in text projection.
- Added support for saving individual frames and refined output video generation process.
2026-01-12 14:04:53 +01:00
Prince Canuma
d1ca36a315
initial commit (LTX-2)
2026-01-11 23:48:33 +01:00
