Bk-sdm: A lightweight, fast, and cheap version of stable diffusion
Abstract Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high
computing demands due to billion-scale parameters. To enhance efficiency, recent studies …
computing demands due to billion-scale parameters. To enhance efficiency, recent studies …
Bk-sdm: Architecturally compressed stable diffusion for efficient text-to-image generation
Exceptional text-to-image (T2I) generation results of Stable Diffusion models (SDMs) come
with substantial computational demands. To resolve this issue, recent research on efficient …
with substantial computational demands. To resolve this issue, recent research on efficient …
Compressing image-to-image translation gans using local density structures on their learned manifold
Generative Adversarial Networks (GANs) have shown remarkable success in modeling
complex data distributions for image-to-image translation. Still, their high computational …
complex data distributions for image-to-image translation. Still, their high computational …
Discriminator-cooperated feature map distillation for gan compression
Despite excellent performance in image generation, Generative Adversarial Networks
(GANs) are notorious for its requirements of enormous storage and intensive computation …
(GANs) are notorious for its requirements of enormous storage and intensive computation …
[图书][B] Computer Vision-ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXIV.
A Leonardis - 2024 - books.google.com
The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes
the refereed proceedings of the 18th European Conference on Computer Vision, ECCV …
the refereed proceedings of the 18th European Conference on Computer Vision, ECCV …
Mixing Pruning and Distillation for Lighter Diffusion Models
D Dell'Olio - amslaurea.unibo.it
Diffusion Models (DMs) represent the state-of-the-art in image generation tasks in terms of
training stability and sample quality, but their sampling procedure is highly resource …
training stability and sample quality, but their sampling procedure is highly resource …