?cid=2154d3d7ktwmgyvz9330lom8wh6ruosfkxx29q3y0x504vga&rid=giphy.gif&ct=g
Midjourney
Discussion
Ah, cool. I have no idea what that means. Is that an app/program?
?cid=2154d3d7ms066osu71b6yk6pem22xwo49nfiwp2mcjo7okvk&rid=giphy.gif&ct=g
Yea. It uses text prompts to generate images.
Ah, cool. You seem to have much better success with that then I have. Then again I mostly just try to break with overlapping human forms 😂… AI does not seem to understand human flesh or individuality😬😳 …works better w objects
?cid=2154d3d7m0rvj7it5alix9c7dy8b0k3rsw18q0wacssy6nag&rid=giphy.gif&ct=g
Takes some practice to know what works. Different models do different things. Prompts can return wildly different results depending on what you enter. I’ve generated probably over 5000 images now so I have a decent grasp of what works.
Human shape and faces are actually well understood by AI. It’s the hands it has the most difficult time with. Midjourney specifically does poorly with more than one subject.
🤙 Will have to try that some then. I’ve generally noticed the same, faces are usually alright, but if two people dare hug… ooooh boy they must need be a flesh monster with interconnected limbs 😳🤣🤣😅😰
?cid=2154d3d7o2ialxz6k1q289cg6ei7k08heb5mpg6a1s6x4uac&rid=giphy.gif&ct=g
Another options is dall-e for a paid version, or stable journey for self host… but you have to have a good graphic card
Stable diffusion is not bad and can make some great images too.
That’s what I’m using… midjournry has a very distinct look… shiny I would say… I have to fiddle a lot to get something I’m vibing on… is midjourney easy to get a good result?
If you want truly realistic humans; you have to train a custom model with stable diffusion. Lexica.art has their own model for realistic humans that looks really good.
?cid=2154d3d7cuj1k15ythr0zxtsdba0ehhzkq07jk2yxdisbrdd&rid=giphy.gif&ct=g
Haven't tried that one... can it insert text into an image? MJ completely fails at text.