Instructions to use Kijai/LTX2.3_comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/LTX2.3_comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
ltx-2.3 720p, 832p, 1080p Test
720p:
https://www.bilibili.com/video/BV1RzPxzxE7M/
832p:
https://www.bilibili.com/video/BV1mRPxzLEuA/
1080p:
https://www.bilibili.com/video/BV1Q2PxzDEpD/
The video quality generated by the LTX 2.3 version model has significantly improved
My workflow model matching method
ltx-2.3-22b-dev_transformer_only_fp8_scaled.safetensors
ltx-2.3-22b-distilled-lora-resized_dynamic_rank_159_fro09_bf16.safetensors
My workflow model matching method
ltx-2.3-22b-dev_transformer_only_fp8_scaled.safetensors
ltx-2.3-22b-distilled-lora-resized_dynamic_rank_159_fro09_bf16.safetensors
where to get the resized distiil lora ?
EDIT :found here https://huggingface.co/drbaph/LTX-2.3-FP8/tree/main/LoRA
720p:
https://www.bilibili.com/video/BV1RzPxzxE7M/
832p:
https://www.bilibili.com/video/BV1mRPxzLEuA/
1080p:
https://www.bilibili.com/video/BV1Q2PxzDEpD/The video quality generated by the LTX 2.3 version model has significantly improved
custom audio ? how are you making camera move and lipsync at the same time.. custom audio fails when camera is not static