@lakeside529 seems like it's going to take 2-3 more years until we can actually generate readable manga pages with AI. you would get better results if you generated each image separately and give it more context, but this requires that you put in some effort.
@AmirFFT@brjimc@sneako Tired of explaining what? You made a baseless claim and now youβre fleeing instead of admitting you were wrong. Youβre such a loser lmao.
Three new image models have hit the Arena π
They're named maskingtape, packingtape, and gaffertape.
I'm particularly impressed by the amount of "world knowledge" these models have - as well as the text rendering.
These were simple prompts:
"average engineer's screen" and "young woman taking selfie with Sam Altman"
@testingcatalog@tbpn Is the βa lot of youβ in the room with us? They donβt get more than 100 likes on their videos lmao. What a way to blow money.
CoreWeave cofounder @branninmcbee says older GPUs and servers still have strong demand, even as new generations ramp up:
"Our pricing on Ampere went up during 2025, and our pricing on Hopper stayed within 10% or so of where we started the year."
"Why is that happening? I think it's largely driven by inference and the idea thatβnot every workload needs the latest, greatest GPUs or servers."
"There are different types of workloads that need different compute, and the market is efficiently pairing the right GPUs and servers with the workloads that need them."
"We see incredibly robust demand all the way back to the Ampere generation, which I believe is six years old at this point."
@haele3d that sounds amazing! I was wondering if it would also be possible for the basic mannequin shapes to have sliders in which we can adjust the thickness and length of body parts such as limbs, upper and lower body, neck, etc...