News for hackers. Stuff that matters.
Re:Real-time image editing using latent consistency models by quadrature on Friday November 10, 2023 @05:48PM (#38225612)
from https://arxiv.org/abs/2310.04378 it sounds like its a form of distillation of an SDL model. So im guessing it can't be directly trained, but once you have a trained diffusion model you can distil a predictor which cuts out the iterative steps.

While it can do 1-step the output quality looks a ton better with additional steps.

Re:Real-time image editing using latent consistency models by dvrp on Friday November 10, 2023 @05:56PM (#38225679)
You can train it directly. This is from the paper “An LCM demands merely 32 A100 GPUs Hours training for 2-step inference [...]”
Re:Real-time image editing using latent consistency models by T-A on Saturday November 11, 2023 @01:52PM (#38233283)
Let's quote the whole sentence, shall we?

An LCM demands merely 32 A100 GPUs Hours training for 2-step inference, as de- picted in Figure 1. [1]

Now let's look at the caption under Figure 1:

LCMs can be distilled from any pre-trained Stable Diffusion (SD) in only 4,000 training steps (∼32 A100 GPU Hours) for generating high quality 768×768 resolution images in 2∼4 steps or even one step, significantly accelerating text-to-image generation.

The training mentioned in your quote is distillation: it requires a previously trained SD model.

You could have told just by reading the introduction:

We propose a one-stage guided distillation method to efficiently convert a pretrained guided diffusion model into a latent consistency model by solving an augmented PF-ODE.

[1] Section 4.2 in https://arxiv.org/abs/2310.04378