with next to no coding skills and a lot of conversation with Calud, I was able to create a program that inputs an audio file and outputs a text file. For the longest time I had been searching for the right site to use to transcribe for free, but it turns out I could just make it
Finally running image generation natively on my computer using ComfyUI! The training wheels are off and I have much more control now! Here are some results from one of the experiments I have ran so far. Same inputs for all of them (there is a total of 58 of these lol)
(Gpt 4o) I love the ability to build off of a conversation worth of ideas and develop visual styles. These images all had the same starting prompt, but i then told gpt that the artist lives in this era or that era, exploring what holds about the idea and what stylistically shifts