I'm kinda surprised about how hard GenAI fell on its face in the arts (including SD and other video generators). It seemed so promising, when SD came out and it turned out the model fit on people's GPUs. People started making LoRAs, hyperparameter tunes, mixing models, training models for representing characters, ComfyUI and Controlnet came out yada yada.
Then it became synonymous with slop, lowest common denominator content made without care, instead of a tool for enabling people willing to put in a varying level of skill, kinds of expertise and effort, like coding models did.
Then it became synonymous with slop, lowest common denominator content made without care, instead of a tool for enabling people willing to put in a varying level of skill, kinds of expertise and effort, like coding models did.