User LoRA

SD

Hyper SD1.5

Hyper SD1.5 - AI Model cover image
Uploaded at
Aug 29, 2024, 1:34 PM
Uses
18.3k
Reviews
Excellent  (2)
Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

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

Comments