Tagged “images”

Sadly no longer free to access without login. This was a great way to demo current state of image generation

I often don't enjoy these scroll-driven animated articles but this was very well made

more AI experiments on reading and generating images

this is cool. would like to make a converter to generate these from color images

Generating your own teaches the kinds of errors to look for (and what makes things seem less "real"). Will effortless "realistic" generation be possible or there will inevitably be a gap there

Alt-text still better from humans, for now. Interesting comparison of good prompts vs good paragraphs

another image input tool

The very bad image dataset bias issue

animate frames between two images

Simpler image variation than stability-ai one, from another random deep learning company.

A quick look at their website and making a text-to-pokemon model looked interesting.

who is paying for all these gpus

3d model generation (or animation of, at least) from single reference image and a pose

Very easy to follow setup guide for Stable Diffusion, and for running python apps on windows.

Installed windows terminal, setup anaconda prompt to auto init directory. Just some good stupid little tips like that

The dataset used to build krea.ai.
Also discussion of Lexica.
Finding and learning prompts continues to be a whole thing.

Another text-to-image model. This stuff is getting crazy

Comments have some good background on google image search, the cached/full-size images thing, Bing image search, and other things.

this requirement reads like the whole thing was made for a specific cat picture

It works best with 299 x 299px images that depict one specific object.