@DontAnnoyMe9@wizhsaa @EspectroPool54 @bnfw_en no dude, you think budget and time allocation is the same thing. Two different aspects of planning that the production committee has to consider
New @nvidia paper shows how to make text to image models render high resolution images far faster without losing quality.
53x faster 4K on H100, 3.5 seconds on a 5090 with quantization for 138x total speedup.
It speeds up by moving generation into a smaller hidden image space.
It means the model does not create the full detailed image step by step.
Instead, it first works inside a smaller hidden version of the image that has fewer pixels.
Because it processes this smaller space, there are fewer data chunks (called tokens) to handle.
Most models use 8x compression, this uses 32x or 64x, so far fewer tokens.
A direct swap is unstable because old and new latent features do not match.
They add a quick embedding alignment step that trains the patch embedder and output head.
Then they fine tune small LoRA adapters so the main weights stay mostly intact.
For FLUX guidance distilled weights, they fix the training target using outputs with and without text.
----
Paper – arxiv. org/abs/2509.25180
Paper Title: "DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space"
Our #GuildWars2 devs have more elite spec information in store - and will be live on our Twitch channel this Friday, Aug. 1st , at 12:00 p.m. Pacific Time (UTC-7) for a live preview of the new elite specs for the Necromancer, Thief, and Warrior: https://t.co/BGxz74GJTL
Place your wagers, Tyrians! The final reveal of the new elite specs looms - snag the chart, mark your bets, and share your guesses! Glory (and bragging rights) await. #GW2