用戶LoRA

SD

Hyper SD1.5

Hyper SD1.5 - AI Model cover image
上傳時間
2024年8月29日 下午1:34
使用數
18.3k
評論
非常好  (2)
許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

描述

https://huggingface.co/ByteDance/Hyper-SD/ Recommending the 8-step-CFG preserve version as it's much easier and nicer to use.

These are just suggestions. Experimentation is required and you will waste some credits to understand this LoRA. Weight: 0.8 - 1.0 Sampling method: DDIM, Euler, anything! BUT NOT Euler A or DPM 2S a Karras. Because of how ancestral samplers work, you get bland boring outputs below 8 steps. Sampling steps: 7 minimum, 8 recommended.

CFG is still not currently known or explored yet. You may try between 4.0 - 7.0 CFG

TODO: rentry articles going in-depth about hyper-sd capabilities and shortcomings.

Cover artwork: https://pixai.art/artwork/1785900648729422093