and you ask stable diffusion to generate piet code for a slightly better version of stable diffusion (or chatGPT) ...which then you can further use to generate a better version, and so on. Singularity here we come!
Is there some comprehensive source about how to make the most of Stable Diffusion? I find the examples on websites much better than what I've been able to generate — they more closely convey the prompt and have less artifacts/clearly messed up parts
Reproducibility is a big deal. With the Stable Diffusion model as a publicly available test model, using the exact same inputs, especially the seed value for the random number generator, should get you the same picture on subsequent runs or on a different machine. Whether or not ChatGPT is evolving with our input is a secret to make that not the same for their model is known only to OpenAI.
reply