I've been playing with stable diffusion and got some really fun results. Here are a few of my favorites:
this post was submitted on 29 Sep 2022
28 points (100.0% liked)
Technology
34920 readers
180 users here now
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
founded 5 years ago
MODERATORS
and a few more abstract ones
these look amazing, what was the prompt ?
Oh here are a few I tried to get the pics above. Each time you run it something new comes out, but they have a certain common feel to them based on the prompt.
- a face made of golden hour, spitting acid, Lightpainting, Tom Bagshaw, abstract, Set in the Rocky Mountains
- A cat portrait in space, nebula by Dan Mumford and Umberto Boccioni, oil on canvas
- celestial crow with a nebula background by Guweiz and Dan Mumford, oil on canvas
- a woman hiding in the shadows on a ruined world, futuristic post-apocalyptic vibe, all the streets are on fire and smoke, humble philosopher
this site has a lot of fun prompts to try, and I find recombining them can get really neat results https://arthub.ai/
Just make it open source and self-hostable. Then you don't have to waste server time for people requesting sus pictures of amogus!
Just use stable diffusion https://www.assemblyai.com/blog/how-to-run-stable-diffusion-locally-to-generate-images/
Dall-e and Craiyon are OpenSource and free to use, while Dalle2 is paid proprietary soft (well. not very expensive anyway). There are currently a lot of text to image AI services out there, some free and others paid soft, like Nightcafe, Deepdream generator, Dreamstudio, Wombo Art, etc. I think that in the future with this AI hype there would be a lot more AI apps and services. Currently I use an AI search assistant, still in alpha but works like a charm, apart it's the most private search engine I know, no ads, no trackers and a own Reader mode for websites that permits to read the page without the need to enter.
Registration requires mandatory phone number verification. No thanks.
I know, but it's a tecnical information that its now online. There are also a lot of alternatives out there which are free to use, like Nightcafe, also very good or even Dall-E (the first) or better Craiyon, completly free and some others which you can find in AlternativeTo. There is also ArtBreeder (no is text2image, it works in another manner), which is also paid, but permits a free use, but limit the up or downloads of images to mix, but there are a lot of images you can use for source and instead of download, well, use simply a screenshot ;)