I have a couple of questions regarding model training and input methods that I would greatly appreciate your insights on:
If I have three types of conditions, such as color condition, segmentation condition, and depth condition, is it feasible to train a model using these multiple conditions simultaneously?
Is it possible to use embeddings as input for prompts instead of traditional text captions? If so, could you provide some guidance or resources on how to implement this?
Thank you very much for your time and assistance.
I hope this message finds you well.
I have a couple of questions regarding model training and input methods that I would greatly appreciate your insights on:
If I have three types of conditions, such as color condition, segmentation condition, and depth condition, is it feasible to train a model using these multiple conditions simultaneously? Is it possible to use embeddings as input for prompts instead of traditional text captions? If so, could you provide some guidance or resources on how to implement this? Thank you very much for your time and assistance.