Prince Canuma ce39e744c3 Refactor VideoEncoder to initialize from VideoEncoderModelConfig, enhancing configuration management. Add methods for weight sanitization and loading from pretrained models, improving model usability and integration with existing workflows.

2026-01-23 17:59:57 +01:00

..

__init__.py

Refactor VideoEncoder to initialize from VideoEncoderModelConfig, enhancing configuration management. Add methods for weight sanitization and loading from pretrained models, improving model usability and integration with existing workflows.

2026-01-23 17:59:57 +01:00

convolution.py

initial commit (LTX-2)

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

decoder.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

encoder.py

Refactor weight loading and sanitization processes for audio models

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

ops.py

Enhance precision in denormalization and normalization processes

2026-01-17 01:14:29 +01:00

resnet.py

Add image-to-video (I2V) conditioning support

2026-01-17 00:19:52 +01:00

sampling.py

Add streaming support to video generation

2026-01-17 23:17:08 +01:00

tiling.py

Enhance video generation with progress bar for streaming and remove debug prints from tiling decoder

2026-01-17 23:53:53 +01:00

video_vae.py

Refactor VideoEncoder to initialize from VideoEncoderModelConfig, enhancing configuration management. Add methods for weight sanitization and loading from pretrained models, improving model usability and integration with existing workflows.

2026-01-23 17:59:57 +01:00