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

..

audio_vae

Refactor weight loading and sanitization processes for audio models

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

prompts

Add prompt enhancement feature to video generation

2026-01-15 14:31:00 +01:00

video_vae

Add LTX-2.3 model architecture with prompt-conditioned adaptive layer normalization (adaln) support. Introduce gating mechanisms in attention modules and update transformer configurations to accommodate new parameters. Refactor video and audio processing to utilize adaptive normalization, improving model flexibility and performance. Update weight loading and initialization logic to support dynamic block structures in the decoder.

2026-03-10 16:47:36 +01:00

__init__.py

add audio

2026-01-16 01:15:22 +01:00

adaln.py

initial commit (LTX-2)

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

attention.py

Add LTX-2.3 model architecture with prompt-conditioned adaptive layer normalization (adaln) support. Introduce gating mechanisms in attention modules and update transformer configurations to accommodate new parameters. Refactor video and audio processing to utilize adaptive normalization, improving model flexibility and performance. Update weight loading and initialization logic to support dynamic block structures in the decoder.

2026-03-10 16:47:36 +01:00

config.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

convert.py

Fix timestep_conditioning logic in infer_vae_decoder_config to ensure consistent behavior based on has_timestep flag.

2026-03-11 18:30:29 +01:00

feed_forward.py

initial commit (LTX-2)

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

ltx.py

Add LTX-2.3 model architecture with prompt-conditioned adaptive layer normalization (adaln) support. Introduce gating mechanisms in attention modules and update transformer configurations to accommodate new parameters. Refactor video and audio processing to utilize adaptive normalization, improving model flexibility and performance. Update weight loading and initialization logic to support dynamic block structures in the decoder.

2026-03-10 16:47:36 +01:00

rope.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

text_encoder.py

Update .gitignore to exclude additional configuration and model files. Modify generate.py to enhance console output with rescale parameter and adjust default values for inference steps and CFG scale. Refactor text encoder to align positional embedding max position with PyTorch defaults, improving compatibility and performance.

2026-03-12 17:13:43 +01:00

text_projection.py

- Refactor video generation script

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

transformer.py

Add LTX-2.3 model architecture with prompt-conditioned adaptive layer normalization (adaln) support. Introduce gating mechanisms in attention modules and update transformer configurations to accommodate new parameters. Refactor video and audio processing to utilize adaptive normalization, improving model flexibility and performance. Update weight loading and initialization logic to support dynamic block structures in the decoder.

2026-03-10 16:47:36 +01:00

upsampler.py

Add LTX-2.3 model architecture with prompt-conditioned adaptive layer normalization (adaln) support. Introduce gating mechanisms in attention modules and update transformer configurations to accommodate new parameters. Refactor video and audio processing to utilize adaptive normalization, improving model flexibility and performance. Update weight loading and initialization logic to support dynamic block structures in the decoder.

2026-03-10 16:47:36 +01:00