Prince Canuma e0aafd72fc Refactor generate.py to ensure temporal coordinates and position grids are processed in bfloat16 for consistency with PyTorch's precision behavior. Update denoise_dev_av function to apply standard ratio rescaling for audio and video guidance, enhancing numerical fidelity and model compatibility.

2026-03-12 21:26:38 +01:00

..

components

Refactor model loading in generate.py to use dynamic model paths for audio and video components. Simplify weight loading logic in LTX2TextEncoder to accommodate both monolithic and reformatted model structures. Introduce a check for existing model paths in get_model_path function to enhance robustness.

2026-03-09 15:51:21 +01:00

conditioning

ensure dtype cast

2026-01-17 13:03:48 +01:00

models

Refactor generate.py to ensure temporal coordinates and position grids are processed in bfloat16 for consistency with PyTorch's precision behavior. Update denoise_dev_av function to apply standard ratio rescaling for audio and video guidance, enhancing numerical fidelity and model compatibility.

2026-03-12 21:26:38 +01:00

__init__.py

Refactor video generation and model loading processes to utilize from_pretrained methods for VideoEncoder and VideoDecoder. Update denoising functions to include a cfg_rescale parameter for improved artifact reduction. Ensure consistent dtype handling across audio and video processing, enhancing precision and aligning with PyTorch behavior.

2026-01-23 17:39:02 +01:00

convert.py

Refactor weight loading and sanitization processes for audio models

2026-01-23 17:31:25 +01:00

generate.py

Refactor generate.py to ensure temporal coordinates and position grids are processed in bfloat16 for consistency with PyTorch's precision behavior. Update denoise_dev_av function to apply standard ratio rescaling for audio and video guidance, enhancing numerical fidelity and model compatibility.

2026-03-12 21:26:38 +01:00

postprocess.py

initial commit (LTX-2)

2026-01-11 23:48:33 +01:00

text_projection.py

- Refactor video generation script

2026-01-12 14:04:53 +01:00

utils.py

Refactor model loading in generate.py to use dynamic model paths for audio and video components. Simplify weight loading logic in LTX2TextEncoder to accommodate both monolithic and reformatted model structures. Introduce a check for existing model paths in get_model_path function to enhance robustness.

2026-03-09 15:51:21 +01:00

version.py

setup

2026-01-12 16:17:45 +01:00