Reimu Hakurei commited on
Commit
9dcd38d
1 Parent(s): d3090d5

add notice

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -27,14 +27,14 @@ We also support a [Gradio](https://github.com/gradio-app/gradio) web ui with dif
27
 
28
  The model originally used for fine-tuning is [Stable Diffusion V1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4), which is a latent image diffusion model trained on [LAION2B-en](https://huggingface.co/datasets/laion/laion2B-en).
29
 
30
- The current model has been fine-tuned with a learning rate of 5.0e-6 for 4 epochs on 56k Danbooru text-image pairs which all have an aesthetic rating greater than `6.0`.
 
 
31
 
32
  ## Training Data & Annotative Prompting
33
 
34
  The data used for fine-tuning has come from a random sample of 56k Danbooru images, which were filtered based on [CLIP Aesthetic Scoring](https://github.com/christophschuhmann/improved-aesthetic-predictor) where only images with an aesthetic score greater than `6.0` were used.
35
 
36
- Captions are Danbooru-style captions.
37
-
38
  ## License
39
 
40
  This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
 
27
 
28
  The model originally used for fine-tuning is [Stable Diffusion V1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4), which is a latent image diffusion model trained on [LAION2B-en](https://huggingface.co/datasets/laion/laion2B-en).
29
 
30
+ The current model has been fine-tuned with a learning rate of 5.0e-6 for 4 epochs on 56k text-image pairs obtained through Danbooru which all have an aesthetic rating greater than `6.0`.
31
+
32
+ **Note:** This project has **no affiliation with Danbooru.**
33
 
34
  ## Training Data & Annotative Prompting
35
 
36
  The data used for fine-tuning has come from a random sample of 56k Danbooru images, which were filtered based on [CLIP Aesthetic Scoring](https://github.com/christophschuhmann/improved-aesthetic-predictor) where only images with an aesthetic score greater than `6.0` were used.
37
 
 
 
38
  ## License
39
 
40
  This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.