my character continuity is starting to actually get on track. I know this is short but for me it is light years ahead of where I was just yesterday. I was was previously trying to train a character using LoRa and that still got me a different character in every clip. But, just using one one image and instead of using text to describe the character, I'm giving it the single character reference and then telling the ai what I want that character to do. This was a case where I was giving too much context. I know it isn't perfect but I'm still pleased with where I am at the present