NUS Jeveration generates 512px images in one forward pass, 78ms on H200, 122x faster

multimodalart · x · 2026-11-19

Jeveration from NUS applies the 'System One' approach to image generation: a frozen vision-language model outputs an entire 512px image in a single forward pass.

Demo images (a sunflower still life, a cat holding a camera) look plausible. multimodalart: quality is far from SOTA, but the speed is insane.

Related event: Jeveration: Frozen VLM Generates 512px Images in One Forward Pass, 78ms(5 posts)→

Original post →

More from Multimodal

Multimodal channel →