etweedy commited on
Commit
d0d8e99
1 Parent(s): b5ed7d0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -10
README.md CHANGED
@@ -1,17 +1,16 @@
1
  ---
2
- license: creativeml-openrail-m
3
  tags:
4
  - text-to-image
5
  ---
6
- ### Tessa3 on Stable Diffusion via Dreambooth
7
- #### model by etweedy
8
- This your the Stable Diffusion model fine-tuned the Tessa3 concept taught to Stable Diffusion with Dreambooth.
9
- It can be used by modifying the `instance_prompt`: **a photo of \<tessa\> dog**
10
 
11
- You can also train your own concepts and upload them to the library by using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb).
12
- And 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), [Spaces with the Public Concepts loaded](https://huggingface.co/spaces/sd-dreambooth-library/stable-diffusion-dreambooth-concepts)
13
 
14
- Here are the images used for training this concept:
15
  ![image 0](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/13.jpeg)
16
  ![image 1](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/14.jpeg)
17
  ![image 2](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/10.jpeg)
@@ -26,5 +25,4 @@ Here are the images used for training this concept:
26
  ![image 11](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/4.jpeg)
27
  ![image 12](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/1.jpeg)
28
  ![image 13](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/7.jpeg)
29
- ![image 14](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/0.jpeg)
30
-
 
1
  ---
2
+ license: apache-2.0
3
  tags:
4
  - text-to-image
5
  ---
6
+ ### Tessa on Stable Diffusion v1.5 via Dreambooth
7
+ ####
8
+ This is a Stable Diffusion (v1.5) model fine-tuned on the concept of my dog, Tessa, usiung the Dreambooth method: https://dreambooth.github.io/
9
+ To use the model, try modifying the basic prompt: \"**a photo of \<tessa\> dog**\".
10
 
11
+ The model was fine-tuned for 1200 steps with a learning rate of 2e-6, using 15 images of Tessa and 500 class regularization images. The class images were generated in advance by Stable Diffusion v1.5 using the prompt "Photo of a dog".
 
12
 
13
+ Here are the images of Tessa used for training this concept:
14
  ![image 0](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/13.jpeg)
15
  ![image 1](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/14.jpeg)
16
  ![image 2](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/10.jpeg)
 
25
  ![image 11](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/4.jpeg)
26
  ![image 12](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/1.jpeg)
27
  ![image 13](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/7.jpeg)
28
+ ![image 14](https://huggingface.co/etweedy/tessa3/resolve/main/concept_images/0.jpeg)