LCM-LoRA: A Universal Stable-Diffusion Acceleration Module · HackerPapers discussions

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module — HN submission

Thu, 16 Nov 2023 09:13:47 GMT

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module — HN submission

Wed, 15 Nov 2023 12:04:48 GMT

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

8 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module — mentioned by vipermu

Fri, 10 Nov 2023 22:59:01 GMT

indeed; we're able to make it work with SDXL thanks to a new technique that got released yesterday called LCM-LoRA. with LCM-LoRA you can turn models like SDXL into LCMs without need for training and you can add other style LoRAs like the ones you find on civit.ai in case you're interested, here's the technical report about LCM-LoRA: https://arxiv.org/abs/2311.05556

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

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module — 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.