this post was submitted on 01 Dec 2023
13 points (100.0% liked)

Stable Diffusion

4337 readers
1 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 2 years ago
MODERATORS
 

SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. We release SD-Turbo as a research artifact, and to study small, distilled text-to-image models. For increased quality and prompt understanding, we recommend SDXL-Turbo.

Model Description

SD-Turbo is a distilled version of Stable Diffusion 2.1, trained for real-time synthesis. SD-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.

you are viewing a single comment's thread
view the rest of the comments
[–] Blaze@discuss.tchncs.de 1 points 1 year ago

I don't mind it to be honest