Video-to-Video
PEFT
English
video-restoration
audio-video
audio-enhancement
omnivr-flash
lora
ltx-video
Instructions to use xin1u/OmniVR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use xin1u/OmniVR with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download ckpt/tinydecoder/README.md from xin1u/OmniVR: direct link, hf CLI and curl.
- Browser
- Download file 777 Bytes
-
https://huggingface.co/xin1u/OmniVR/resolve/main/ckpt/tinydecoder/README.md
- Command line
-
hf download hf://xin1u/OmniVR/ckpt/tinydecoder/README.md
-
curl -L -o README.md https://huggingface.co/xin1u/OmniVR/resolve/main/ckpt/tinydecoder/README.md
777 Bytes
| # Optional legacy TinyDecoder | |
| `taeltx2_3_wide.pth` is the decoder-only TAEHV checkpoint from the earlier | |
| OmniVR release. Its implementation is bundled in | |
| [`inference_tiny_decoder.py`](../../packages/omini-restore-trainer/scripts/inference_tiny_decoder.py). | |
| Attribution and its MIT license are retained in [NOTICE](../../NOTICE). | |
| The multistep entry point uses the full LTX video VAE by default. To select | |
| the legacy decoder explicitly: | |
| ```bash | |
| hf download xin1u/OmniVR tinydecoder/taeltx2_3_wide.pth --local-dir ckpt | |
| # Add this option to the multistep command: | |
| # --tiny_decoder ckpt/tinydecoder/taeltx2_3_wide.pth | |
| ``` | |
| This checkpoint cannot replace the Flash Turbo VAE: Flash requires both an | |
| UltraTinyVAE encoder and decoder matching the bundled `configs/turbo_vae.json`. | |