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.
The first line of the bot’s readme states:
It makes the Lemmy post visible to Mastodon users who search for or follow that tag; otherwise, since Lemmy doesn’t support tags and won’t for the foreseeable future, the only way for Mastodon users to find these posts would be to follow the Lemmy community itself (Lemmy communities show up as individual users in Mastodon), and that would require them to know it exists. The more people see a post, the more likely it is that a discussion will take place.
If you don’t want to see the bot’s posts since you’re using Lemmy directly, the bio states you’re free to block or mute it if you find its posts annoying.
This makes me think I should probably have a look and implement it for another community