web dev and digital artist making [email protected]

  • 1 Post
  • 15 Comments
Joined 1 year ago
cake
Cake day: June 15th, 2023

help-circle

  • You might be right, I definitely see your point. ActivityPub adds a whole new layer to this too. In the end though, isn’t the content we post no different than anything else published on the Internet? I guess it’s important to note that technically nothing public can be 100% prevented from being used in unwanted ways. However, there might be other ways (legally, socially, etc.) we could discourage it.

    Regardless, I’d love to get a better sense of how much this matters to us here on Lemmy—or if it should even matter in the first place








  • 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…”