That doesn't pass the sniff test, many other pages on knowyourmeme correctly attribute memes to 4chan.
If you were right that would be easily verifiable. Do you have an example of a post dated before 2018? Maybe you're getting tricked by the fact that 2018 was 8 years ago?
I think you are taking their point literally, its not that knowyourmeme is not crediting 4chan, its that the racism/edge is polished off presenting a more mainstream version of many memes.
It's funny to see as a joke, but you can go the other way with this too. Image editing models and LoRAs for "previz-to-render upscaling" workflows are actually incredibly useful.
I was just writing about this (scroll about halfway down to the images of Sam Altman - though if you like that, do watch the second video):
The best model I've found for this, that almost bakes in full ControlNet capability, is oddly gpt-image-1.5. It's absolutely OP at understanding how to turn low-fidelity renders into final draft upscales.
It's funny how know your meme has to sanitize the 4chan out of memes.
The 'how society would look without x' has been a racist trope on 4chan since way before the cited examples.
That doesn't pass the sniff test, many other pages on knowyourmeme correctly attribute memes to 4chan.
If you were right that would be easily verifiable. Do you have an example of a post dated before 2018? Maybe you're getting tricked by the fact that 2018 was 8 years ago?
12 times in a 2015 archive of /b/?
https://github.com/johnschriner/4chan-a-b-pol/blob/master/4A...
I think you are taking their point literally, its not that knowyourmeme is not crediting 4chan, its that the racism/edge is polished off presenting a more mainstream version of many memes.
1 reply →
> If you were right that would be easily verifiable. Do you have an example of a post dated before 2018?
How?
1 reply →
It's funny to see as a joke, but you can go the other way with this too. Image editing models and LoRAs for "previz-to-render upscaling" workflows are actually incredibly useful.
I was just writing about this (scroll about halfway down to the images of Sam Altman - though if you like that, do watch the second video):
https://getartcraft.com/news/world-models-for-film
The best model I've found for this, that almost bakes in full ControlNet capability, is oddly gpt-image-1.5. It's absolutely OP at understanding how to turn low-fidelity renders into final draft upscales.
Here are some older experiments:
https://imgur.com/a/previz-to-image-gpt-image-1-5-3fq042U
https://imgur.com/gallery/previz-to-image-gpt-image-1-x8t1ij...
https://imgur.com/aOliGY4
I just wish it didn't require invoking such heavy-weight, slow, and expensive models to do this. I'm sure open models will do this work soon, though.
What’s going on with that (robot?) dog leash?