Recently, I have been busy dealing with some trivial matters, which has affected the progress of AI learning. Now, I will record my current thoughts.
I am trying to use chatGPT and Midjourney as AI assistants, aiming to achieve the effect of one person being equivalent to an army. I focus on thinking about the core content and let AI assist in implementation to see if it can improve work efficiency.
I have been using Midjourney (MJ) for a while now, and the problem I have encountered is that the generated images are quite different from what I have in mind. If it is a simple idea, such as "a man standing on a mountain looking into the distance," MJ can generate many different styles of images, which helps expand my thinking. However, when the detailed requirements increase, the situation becomes difficult to control. For example, when I add the detail of "holding a robe in hand," MJ has difficulty accurately presenting this scene. It either wears the robe or includes a character related to the robe. In other words, if the precision of expressing the content in the image is not high, MJ's generation effect is quite good, but if higher precision is required, the accuracy needs to be improved through continuous prompts. I still need to delve into this aspect of learning, luckily, I have found a good learning resource that I can refer to, which is the Midjourney Learning Guide.
Next, I plan to study SD and compare it with MJ to understand the advantages and disadvantages of each.