lavaman131
commited on
Commit
•
9724dc1
1
Parent(s):
6315993
added examples
Browse files
README.md
CHANGED
@@ -16,13 +16,17 @@ instance_prompt: disney style
|
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
|
19 |
-
#
|
20 |
|
21 |
-
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5 with fine-tuning of the text encoder. The weights were trained from a popular animation studio using [DreamBooth](https://dreambooth.github.io/). Use the tokens **_disney style_** in your prompts for the effect.
|
22 |
|
23 |
You can find some example images below:
|
24 |
|
25 |
-
|
|
|
|
|
|
|
|
|
26 |
|
27 |
|
28 |
## Intended uses & limitations
|
@@ -45,4 +49,4 @@ As with any diffusion model, playing around with the prompt and classifier-free
|
|
45 |
|
46 |
The model was fine-tuned for 3500 steps on around 200 images of modern Disney characters, backgrounds, and animals. The ratios for each were 70%, 20%, and 10% respectively on an RTX A5000 GPU (24GB VRAM).
|
47 |
|
48 |
-
The training code used can be found [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py). The regularization images used for training can be found [here](https://github.com/aitrepreneur/SD-Regularization-Images-Style-Dreambooth/tree/main/style_ddim).
|
|
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
|
19 |
+
# Cartoonify
|
20 |
|
21 |
+
This is a dreambooth model derived from `runwayml/stable-diffusion-v1-5` with additional fine-tuning of the text encoder. The weights were trained from a popular animation studio using [DreamBooth](https://dreambooth.github.io/). Use the tokens **_disney style_** in your prompts for the effect.
|
22 |
|
23 |
You can find some example images below:
|
24 |
|
25 |
+
<img width=256 height=256 src="./images/king.png">
|
26 |
+
<img width=256 height=256 src="./images/legend_of_zelda.png">
|
27 |
+
<img width=256 height=256 src="./images/pony.png">
|
28 |
+
<img width=256 height=256 src="./images/princess.png">
|
29 |
+
<img width=256 height=256 src="./images/red_ferrari.png">
|
30 |
|
31 |
|
32 |
## Intended uses & limitations
|
|
|
49 |
|
50 |
The model was fine-tuned for 3500 steps on around 200 images of modern Disney characters, backgrounds, and animals. The ratios for each were 70%, 20%, and 10% respectively on an RTX A5000 GPU (24GB VRAM).
|
51 |
|
52 |
+
The training code used can be found [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py). The regularization images used for training can be found [here](https://github.com/aitrepreneur/SD-Regularization-Images-Style-Dreambooth/tree/main/style_ddim).
|