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
VAE Loader KJ Error
Error(s) in loading state_dict for VideoVAE:
size mismatch for decoder.conv_in.conv.weight: copying a param with shape torch.Size([1024, 128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3, 3]).
size mismatch for decoder.conv_in.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]).
guys i found the solution, you need to update both KJ nodes AND Comfyui to the latest version0.15.1.
Comfyui- now 0.163 for me now. Seems to be working. Thanks cloudinthesky
Confirmed, same outcome for me too. Updated nodes, but needed comfy updated too.
Tried doing both but no luck. Any other suggestions??
Another thing to check is if ComfyUi added a duplicate Custom KJ node into your folder. meaning one would be "file-main" and the new one is just kjnode...