Hugging Face's logo

recoilme
/
sd-pokemon-model-lora-sdxl

Text-to-Image
Diffusers
stable-diffusion-xl
stable-diffusion-xl-diffusers
lora
Model card Files Community
sd-pokemon-model-lora-sdxl / README.md
recoilme's picture
recoilme
End of training
82897bf
preview code
|
raw
history blame
675 Bytes
metadata
license: creativeml-openrail-m
base_model: segmind/SSD-1B
dataset: recoilme/aesthetic_photos_xs
tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - text-to-image
  - diffusers
  - lora
inference: true

LoRA text2image fine-tuning - recoilme/sd-pokemon-model-lora-sdxl

These are LoRA adaption weights for segmind/SSD-1B. The weights were fine-tuned on the recoilme/aesthetic_photos_xs dataset. You can find some example images in the following.

img_0 img_1 img_2 img_3

LoRA for the text encoder was enabled: False.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.