ユーザーLoRA

SD

Hyper SD1.5

Hyper SD1.5 - AI Model cover image
アップロード日時
2024/08/29 13:34
採用数
18.3k
レビュー
大好評  (2)
権限
  • 画像生成と共有を許可する
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

詳細説明

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

コメント