Downloads · 30 days
0
ltx23_extracted_parts
koongrizzly/ltx23_extracted_parts
ltx23_extracted_parts is a machine learning model from koongrizzly. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Access
Public
Updated Jun 7, 2026
Repo size
8.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.2 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 7, 2026
- Updated
- Jun 7, 2026
- SHA
- 22689fbe
Model card
From the Hugging Face model README
tags:
- ltx
- ltx-video
- ltx-2.3
- safetensors
- framevision
- video-generation
LTX 2.3 22B Distilled 1.1 — Split Components
Small split component files extracted from the original LTX 2.3 22B Distilled 1.1 safetensor.
These files are mainly provided for FrameVision and other local workflows that want to avoid repeatedly loading the full large checkpoint just to access small helper components.
Original model source:
https://huggingface.co/Lightricks/LTX-2.3
The original model license and usage rules still apply to these extracted files.
Included files
| File | Purpose |
|---|---|
vocoder.safetensors | Audio vocoder component |
audio_vae.safetensors | Audio VAE component |
vae.safetensors | Video VAE component |
text_embedding_projection.safetensors | Text embedding projection component |
Notes
These files were extracted from the original distilled 1.1 safetensor for practical local workflow use.
They are intended as helper components, not as a standalone model.
If you use them in your own project, make sure your use follows the license and terms of the original LTX 2.3 model.
Related project
FrameVision is a free, open-source, portable and offline-focused AI media tool.
These split components are provided to support smoother local LTX 2.3 workflows inside FrameVision.
- License
- mit
- Created
- Jun 7, 2026
- Updated
- Jun 7, 2026