AI art

IMGN Labs / imgnAI

Contextual base image models are a game-changer. 

We’re actively working to deploy these on /imgn - and as you can see, have already got ‘em live on our testing environments.

Basic enough sample below - going to post some of our complex samples once we sign off on showcasing!

e/acc || Building @ /imgn || Dogecoin core dev 2013/14

Nice! so the “Reference Image” advanced option that’s been present on the site hasn’t really been doing anything? That’s basically how it seemed… 😅

Developer/Builder.
Snob.
Fren.
Hodler.
Based mmfer.

We do some music enjoying. We shoot some hoops. We degen with the homies.

just a wee bit of alfa here

If you like the video gen previews, make sure you're on discord and have linked your webapp account 👀

Ahh ok. I figured it was most likely me not understanding how to use it.

I somehow didn’t know about the discord. Will be joining that today.

Thanks for the quality info, legend!

228 👏

It does, it pre-seeds the noise! But it often needs manual adjustment / strength ratios to work well.

It doesn’t “edit” an image like a contextual model though - you can gen an image of an airstrip in the shape of a cat for example, but you can’t directly say “hey put this cat in a cute jumper” when it’s just pre-seeding the noise.

Try discord for reference images for img2img if the webapp isn’t giving you good results - I’ve done a lot of manual tuning on that to make the automated results a bit better. Try on the ani or nai models in particular! Flux can be very finicky with it.