Edit model card

LoRA Kimono for WD 1.5 Beta 2 Aesthetic

This is LoRA that draws beautiful kimono and yukata designs.

  • LoRA Kimono Ver. 0.6 for WD 1.5 Beta 2 Aesthetic

Usage

  • Use the AUTOMATIC1111's stable-diffusion-webui.
  • Install the latest version of the sd-webui-additional-networks extension from its URL in the "Extensions" tab on the Web UI.
  • Copy the LoRA file to the "stable-diffusion-webui/extensions/sd-webui-additional-networks/models/lora" folder.
  • Select the LoRA file and click "Send to * number" in the "Additional Networks" tab on the Web UI.
  • In the "txt2img" or "img2img" tab, enable the 'Additional Networks' option, verify the LoRA name, and adjust the weight as needed.
  • Select the wd-1-5-beta2-aesthetic-fp16.safetensors as Stable Diffusion checkpoint.

Release Notes

  • Ver. 0.6 2023/04/20: Increased dim to 16 and trained using bucket
  • Ver. 0.5 2023/04/15: Increased dim from 4 to 8
  • Ver. 0.4 2023/04/07: Cleansed kimono dataset
  • Ver. 0.3 2023/03/17: Restrained flashiness
  • Ver. 0.2 2023/03/16: Added images for regularization
  • Ver. 0.1 2023/03/15

Example images

Example image

Example image

  • Example prompt : kimono, yukata clothing, traditional geisha clothing, red kimono with flower patterns, classy yukata clothing, skilled geisha, female geisha girl, traditional colors, elegant girl, geisha, geisha photo portrait, highly detailed kimono, upper body portrait, smile, (anime:1.2), (waifu, best aesthetic, new, newest, best quality, masterpiece, extremely detailed:1.2)

  • Example useful words : kimono, yukata, geisha

License

LoRA Kimono under the Fair AI Public License 1.0-SD. If any derivative of this model is made, please share your changes accordingly.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Model tree for Uminosachi/lora-kimono_sd-2-1

Adapter
this model