graysonk

I enjoy doing local image generation and this is one thing that the community around that has really optimized.

In some workflows you might have 20 different models doing their specialized tasks. Pose detection, hand/eye/face detailers, classifiers, refiners, up scalers, taggers, etc can all use their own models and that’s not even the including the model(s) used for the actual image generation part.

I’m interested to see the optimization when this concept gets applied to other general ai tasks.

“What trying to protect the feelings of a group of people who will never care about me taught me about b2b sales”

It’s like you’re trying to fill out a bingo card of “obviously written by ai” markers

This is an insane level of projection

Crazy. It’s almost as if we are on a news site for hackers

This is one of those comments you write after taking a “How to market your product online 100% free!!” classes

Dang can ban me if he wants but look at this dudes comment history. 100% nothing but shilling his product

The absence of a data point is still an identifiable data point

I thought that was just Real Estate Brokers and not Agents?

I’d agree with you if Ireland didn’t exist

Really? My turning point was when he called out companies for not hiring him and then said he did more work than the engineering team in 3 months

> Lucky for you I'm not selling anything

Hmm there is a pretty big "Pricing" section in the middle of the page for me