This PR adds a pipeline tag, making sure the model can be found at https://huggingface.co/models?pipeline_tag=image-to-image, as well as
adding a link to the paper [Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models](https://huggingface.co/papers/2412.18605)
Upload cropsmallEx03/dino_weight.pt with huggingface_hub
