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

Add image-to-video (I2V) conditioning support

Browse Source 
- Introduced `load_image`, `prepare_image_for_encoding`, and `apply_conditioning` functions for handling image inputs and conditioning during video generation.
- Enhanced `generate_video` and `denoise_av` functions to accept optional image inputs for I2V conditioning.
- Updated command-line interface to include parameters for image conditioning, such as `--image`, `--image-strength`, and `--image-frame-idx`.
- Added new `VideoConditionByLatentIndex` and `LatentState` classes for managing latent states with conditioning.
- Implemented VAE encoder loading and image encoding for conditioning in the video generation process.d
This commit is contained in:
Prince Canuma
2026-01-17 00:19:52 +01:00
parent 5f86e881d7
commit 146f5d2981
11 changed files with 937 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mlx_video/models/ltx/video_vae/__init__.py
View File

@@ -1 +1,3 @@
from mlx_video.models.ltx.video_vae.video_vae import VideoEncoder, VideoDecoder
from mlx_video.models.ltx.video_vae.encoder import load_vae_encoder, encode_image
from mlx_video.models.ltx.video_vae.decoder import load_vae_decoder, LTX2VideoDecoder