Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference · HackerPapers discussions

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference — mentioned by T-A

Sat, 11 Nov 2023 18:52:17 GMT

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…

Paper and discussion history. A mention is not an endorsement.

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference — mentioned by quadrature

Fri, 10 Nov 2023 22:48:29 GMT

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.

Paper and discussion history. A mention is not an endorsement.

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference — mentioned by vipermu

Fri, 10 Nov 2023 20:19:46 GMT

it uses a new technique called "consistency" that lets latent diffusion models to predict images in much fewer steps. some links here: - https://arxiv.org/abs/2310.04378 - https://arxiv.org/abs/2311.05556

Paper and discussion history. A mention is not an endorsement.