n0p/mlx-video
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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.

Browse Source
This commit is contained in:
Prince Canuma
2026-01-23 17:59:57 +01:00
parent f8f78aeab5
commit ce39e744c3
3 changed files with 110 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
mlx_video/models/ltx/video_vae/__init__.py
View File

@@ -1,6 +1,6 @@
from mlx_video.models.ltx.video_vae.video_vae import VideoEncoder, VideoDecoder
from mlx_video.models.ltx.video_vae.video_vae import VideoEncoder
from mlx_video.models.ltx.video_vae.encoder import encode_image
from mlx_video.models.ltx.video_vae.decoder import LTX2VideoDecoder
from mlx_video.models.ltx.video_vae.decoder import LTX2VideoDecoder, VideoDecoder
from mlx_video.models.ltx.video_vae.tiling import (
TilingConfig,
SpatialTilingConfig,