Update README.md

README.md

@@ -4,9 +4,12 @@ tags:
 - text-to-image
 - stable-diffusion
 ---
-### abstract_nature_patterns_v2 Dreambooth model trained by apurik-parv with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
-
-
-Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
-Or you can run your new concept via `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb)
+### abstract_nature_patterns_v2 Dreambooth model trained by apurik-parv with  https://github.com/ShivamShrirao/diffusers dreambooth implementation.
 
+The model is an attempt at teaching symmetry and scales associated with nature to SD 1.5 base model.
+This version v2 is trained on better curated images for 40,000 steps. I am still working on finding what the model really does and if it has any impact on the base model.
+With that being said, the following are my findings, at the outset it seems that
+-Images have better symmetry and lighting.
+-Images have less artifacts.
+-Does not seem to work with large canvas such as 1024x1024 the repetition problem isstill there.
+Feel free to experiment with the model.