Hi everyone! I have no talent for art or drawing - this is the reason why I tried to do some experiments with DALL.E 2, the artificial intelligence system which, starting from a description in natural language, tries to draw what you asked.
Now... for sure this artificial intelligence is still far from perfect understanding of language or drawing - but I was so surprised by the results... Surely a real artist could have done better - but I (unskilled as I am) would have done much worse, if I had tried to generate the images myself! I was really impressed.
I'll show you two images that I obtained (albeit a little laboriously - I needed several attempts and several iterations); they are two images of my favorite character, in two different campaigns.
Not bad. I have been considering doing a series myself for filler images, even despite the fact that the images are really composites of other people’s work.
I think that for our own characters, this is pretty awesome stuff. My avatar for here is from such a tool.
Rollback Post to RevisionRollBack
Only a DM since 1980 (3000+ Sessions) / PhD, MS, MA / Mixed, Bi, Trans, Woman / No longer welcome in the US, apparently
Wyrlde: Adventures in the Seven Cities .-=] Lore Book | Patreon | Wyrlde YT [=-. An original Setting for 5e, a whole solar system of adventure. Ongoing updates, exclusies, more. Not Talking About It / Dubbed The Oracle in the Cult of Mythology Nerds
Not bad. I have been considering doing a series myself for filler images, even despite the fact that the images are really composites of other people’s work.
I think that for our own characters, this is pretty awesome stuff. My avatar for here is from such a tool.
Maybe, but it 'composes' quite better than I would! I think it will be a good starting point for those (like me) completely lacking artistic capabilities.
Rollback Post to RevisionRollBack
To post a comment, please login or register a new account.
Hi everyone! I have no talent for art or drawing - this is the reason why I tried to do some experiments with DALL.E 2, the artificial intelligence system which, starting from a description in natural language, tries to draw what you asked.
Now... for sure this artificial intelligence is still far from perfect understanding of language or drawing - but I was so surprised by the results... Surely a real artist could have done better - but I (unskilled as I am) would have done much worse, if I had tried to generate the images myself! I was really impressed.
I'll show you two images that I obtained (albeit a little laboriously - I needed several attempts and several iterations); they are two images of my favorite character, in two different campaigns.
Not bad. I have been considering doing a series myself for filler images, even despite the fact that the images are really composites of other people’s work.
I think that for our own characters, this is pretty awesome stuff. My avatar for here is from such a tool.
Only a DM since 1980 (3000+ Sessions) / PhD, MS, MA / Mixed, Bi, Trans, Woman / No longer welcome in the US, apparently
Wyrlde: Adventures in the Seven Cities
.-=] Lore Book | Patreon | Wyrlde YT [=-.
An original Setting for 5e, a whole solar system of adventure. Ongoing updates, exclusies, more.
Not Talking About It / Dubbed The Oracle in the Cult of Mythology Nerds
Maybe, but it 'composes' quite better than I would! I think it will be a good starting point for those (like me) completely lacking artistic capabilities.