Update README.md

README.md

@@ -17,13 +17,12 @@ sd-wikiart-v2 is a stable diffusion model that has been fine-tuned on the [wikia
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1i7HJlTzVPEirNedDV-TcR5Ok2_8QI6zC?usp=sharing)
 
-<img src=https://cdn.discordapp.com/attachments/930559077170421800/1017265913231327283/unknown.png width=40% height=40%>
 
 ## Model Description
 
 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).
 
-The current model has been fine-tuned with a learning rate of 1e-05 for 1 epoch on 81K text-image pairs from wikiart dataset. Only the attention layers of the model are fine-tuned
+The current model has been fine-tuned with a learning rate of 1e-05 for 1 epoch on 81K text-image pairs from wikiart dataset. Only the attention layers of the model are fine-tuned. This is done to avoid catastrophic forgetting, the model can generate artistic images given specific prompts but still retains most of its previous knowledge.
 
 ## Training Data 
 TODO
@@ -57,7 +56,7 @@ pipe = StableDiffusionPipeline.from_pretrained(
 )
 pipe = pipe.to(device)
 
-prompt = "a painting of eiffel tower in the style of impressionism"
+prompt = "a painting of eiffel tower in the style of surrealism"
 with torch.autocast("cuda"):
     image = pipe(prompt, guidance_scale=7.5).images[0]