I found this on the web for, “no no no no no no no no no no no no no no no no no no”
silas
joined 1 year ago
Talking to a text-to-image model is kinda like meeting someone from a different generation and culture that only half knows your language. You have to spend time with them to be able to communicate with them better and understand the “generational and cultural differences” so to speak.
Try checking out PromptHero or Civit.ai to see what prompts people are using to generate certain things.
Also, most text-to-image models are not made to be conversational and will work better if your prompts are similar to what you’d type in when searching for a photo on Google Images. For example, instead of a command like “Generate a photo for me of a…”, do “Disposable camera portrait photo, from the side, backlight…”
One solution to this would be having humans in the board room instead of parasites. Not sure who’s idea that was
These are some really good thoughts and topics to discuss at this stage in the Fediverse. We must be looking big-picture right now as we move forward. Thanks for pushing the envelope!