Hugging Face's logo

Nilaier
/
Waifu-Diffusers

Text-to-Image
Diffusers
English
StableDiffusionPipeline
stable-diffusion
Model card Files
xet
 Community
22
Nilaier commited on
Commit
a251642
·
1 Parent(s): b0652af

Updated model type

Browse files

I genuinely have no idea what kind of model they've used, but Haru said that his WD 1.4 model was trained on 2.1, so maybe this one too? I have to stop thinking about it too much.

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ A version of Waifu Diffusion v1.4 Float32 Booru 110k model and VAE from Waifu Di
29
 
30
  ## Model Description
31
 
32
- The current model has been fine-tuned on a Waifu Diffusion v1.3 model with 110k anime-styled images using a technique known as aspect ratio bucketing.
33
 
34
  That allows Waifu Diffusion v1.4 to handle different resolutions much better than its previous models.
35
 
 
29
 
30
  ## Model Description
31
 
32
+ The current model has been fine-tuned on a Stable Diffusion 2.1 model with 110k anime-styled images using a technique known as aspect ratio bucketing.
33
 
34
  That allows Waifu Diffusion v1.4 to handle different resolutions much better than its previous models.
35