I don’t disagree about the downside of DALL-E being locked away and expensive. It’s been exciting to see the Cambrian explosion of improvement to stable diffusion since its initial release. This is how AI research should be done and it’s sad that “Open AI” is not actually open.
That being said, for a business use cases, where I want to give it a simple prompt and have a high chance of getting a good usable result, it’s not clear to me that stable diffusion is there yet. Many of the most exciting SD community results seem to be in anime and porn, which can be a bit hard to follow. I guess the use cases that I’m excited about are things like logo generators, blog post image generators, product image thumbnail generators for e-commerce, industrial design, etc.
But please prove me wrong! I’m excited for SD to be the state of the art, it’s definitely better in the long term that’s it’s so accessible. I‘m sure a good guide or blog post about what’s new in stable diffusion outside of anime generation would be an interesting read.
That being said, for a business use cases, where I want to give it a simple prompt and have a high chance of getting a good usable result, it’s not clear to me that stable diffusion is there yet. Many of the most exciting SD community results seem to be in anime and porn, which can be a bit hard to follow. I guess the use cases that I’m excited about are things like logo generators, blog post image generators, product image thumbnail generators for e-commerce, industrial design, etc.
But please prove me wrong! I’m excited for SD to be the state of the art, it’s definitely better in the long term that’s it’s so accessible. I‘m sure a good guide or blog post about what’s new in stable diffusion outside of anime generation would be an interesting read.