Dear DeepLabCut Team,

Thank you for your tremendous work on this invaluable open-source tool. I truly appreciate your efforts and dedication.

I have a suggestion regarding the use of pre-trained superanimal models from the modelzoo for inference. Currently, when using these models purely for inference (without fine-tuning or transfer learning), a project directory and config.yaml file are not created, unlike the standard DeepLabCut projects. This makes it difficult to use the results for further analysis.

It would be very helpful if the inference process with pre-trained superanimal models could also generate a project directory with the necessary files, such as config.yaml. This would ensure consistency across all DeepLabCut projects and make downstream analysis more practical and efficient.

Thank you for considering this suggestion. I hope it contributes to enhancing the usability of DeepLabCut for everyone.

Best regards,