You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi @jozefchutka, I'm still a bit confused about the model itself. I can find some LoRA weights on their Github, but because these are adapters for existing model formats, there's nothing we can add to support them in transformers itself, beyond the support of the actual base architecture.
I am afraid I do not have knowledge deep enough to understand what is missing. Afaik, https://wileewang.github.io/TransPixar/ is the source of the model, can you please look around if you can find whats needed?
Model description
TransPixar AI - Revolutionary AI-powered transparent visual effects generation system developed by Adobe and HKUST researchers
Open source status
Provide useful links for the implementation
https://transpixarai.org/
https://huggingface.co/spaces/wileewang/TransPixar
The text was updated successfully, but these errors were encountered: