Sign In

PCM LoRAs of Stable Diffusion XL for Fast Image Generation

38

529

0

12

Updated: Jun 1, 2024

toollcm-sdxlpcm-sdxl

Verified:

Diffusers

Type

LoRA

Stats

529

0

Reviews

Published

May 31, 2024

Base Model

SDXL 1.0

Hash

AutoV2
82DECF2091
default creator card background decoration

G_U_N

LoRA weights of Stable Diffusion XL for fast image generation.

Important Usage Guidance

  1. Use DDIM or Euler instead of LCM for sampling!

  2. The name of each LoRA weights indicates how many inference steps they should be applied.

  3. The name of each LoRA weights indicates whether they are able to use normal CFGs or small CFGs.

    • NormalCFG means that model equipped with the LoRA can use CFG value 2-9 for generation. For example, Juggernaut XL, in my test, works with 3-5. Hopefully I just find a better way to train normalCFG LoRAs with better visual quality, will update them in the coming days!!!

    • SmallCFG means that the model equipped with the LoRA can use CFG value 1-2 for generation.

About the performance of normal CFG LoRAs.

Important Information

[[paper](https://arxiv.org/abs/2405.18407)]

[[code](https://github.com/G-U-N/Phased-Consistency-Model)]

[[huggingface](https://huggingface.co/wangfuyun)]