this post was submitted on 26 Oct 2023
794 points (95.2% liked)

AI Generated Images

7187 readers
101 users here now

Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.

No explicit violence, gore, or nudity.

This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.

Refer to https://lemmynsfw.com/ for any NSFW imagery.

No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.

AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.

To embed images type:

“![](put image url in here)”

Follow all sh.itjust.works rules.

Community Challenge Past Entries

Related communities:

founded 1 year ago
MODERATORS
noodle@sh.itjust.works
god@sh.itjust.works
theUnlikely@sopuli.xyz
thelsim@sh.itjust.works
M0oP0o@mander.xyz
Deceptichum@quokk.au
794
Your username is the prompt, what did you get? This is mine: (lemmy.world)
submitted 1 year ago* (last edited 1 year ago) by nefurious_krankstar@lemmy.world to c/imageai@sh.itjust.works
1598 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] tal@lemmy.today 6 points 1 year ago* (last edited 1 year ago) (1 children)

One of various web-based services: Midjourney, Dall-E, etc. You'll see people mention some of them in the comments.

Or running locally, on Stable Diffusion, which requires some configuration and a relatively-capable GPU.

This is what my Stable Diffusion instance gives for your username.

Hung_Like_Hodor

Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 0, Size: 1024x1024, Model hash: ebf42d1fae, Model: realmixXL_v15, Token merging ratio: 0.5, Version: v1.5.1

[–] Murdoc@sh.itjust.works 1 points 1 year ago (2 children)

Just spent an hour trying to get sd to work, I guess it doesn't like my system or something. :(

[–] EnderofGames@sh.itjust.works 3 points 1 year ago (1 children)

Stable Diffusion does require some setup and knowledge, for occasional hobbyist use it's probably too much to ask for.

Midjourney sadly stopped free trials. But DALL-E and ChatGPT (OpenAI) have research/free use available. And DALL-E 3 costs money through OpenAI, but if you just search for "Bing image generator" it uses DALL-E 3. There are other free generation tools, and some examples on using SD and branches of SD online if you get interested in seeing who can do what. Sadly most free tools have censorship rules, but hopefully "hung" won't trip any of them.

[–] Murdoc@sh.itjust.works 1 points 1 year ago (1 children)

Thanks! Know anything about InvokeAI? I've managed to get that to work, so it's just a matter of finding a good model for it to use. And getting better with prompts of course, but communities like this are helping a lot there.

[–] EnderofGames@sh.itjust.works 1 points 1 year ago

I haven't tried Invoke, no. My SD journey is at a standstill because I haven't learned how to convert safetensors into working model files, and I haven't tried in a few months.

[–] woobie@lemmy.world 1 points 1 year ago

Might be easiest to use the Bing Image Generator which uses Dall-E-3 as the backend. It's currently free.