matallanas
commited on
Commit
·
7491a23
1
Parent(s):
b4fb90e
Update README.md
Browse filesUpdate Model card
README.md
CHANGED
@@ -1,18 +1,32 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
library_name: keras
|
3 |
---
|
4 |
|
5 |
## Model description
|
6 |
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
## Intended uses & limitations
|
10 |
|
11 |
-
|
12 |
|
13 |
## Training and evaluation data
|
14 |
|
15 |
-
|
16 |
|
17 |
## Training procedure
|
18 |
|
@@ -51,4 +65,29 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
![Model Image](./model.png)
|
53 |
|
54 |
-
</details>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- stable-diffusion
|
6 |
+
- text-to-image
|
7 |
+
- keras-dreambooth
|
8 |
+
- wildcard
|
9 |
+
license: creativeml-openrail-m
|
10 |
+
inference: true
|
11 |
library_name: keras
|
12 |
---
|
13 |
|
14 |
## Model description
|
15 |
|
16 |
+
The Ignatius Farray dreambooth model would be a sleek and modern diffusion model designed to transport users into a world of absurdity and hilarity.
|
17 |
+
I cannot promise that all the images would be adorned with bright, eye-catching colors and images that reflect Ignatius' unique sense of style and humor.
|
18 |
+
|
19 |
+
## Images generated by model
|
20 |
+
|
21 |
+
![summary_image](./ignatius_summary.png)
|
22 |
|
23 |
## Intended uses & limitations
|
24 |
|
25 |
+
You can use to create images based on Ignatius and put him in different situations. Try not to use for bad purpose and use the "commedia" on it.
|
26 |
|
27 |
## Training and evaluation data
|
28 |
|
29 |
+
To train this model, this was the training [notebook](https://colab.research.google.com/github/huggingface/community-events/blob/main/keras-dreambooth-sprint/Dreambooth_on_Hub.ipynb) and the trainig dataset was this [one](https://huggingface.co/datasets/matallanas/ignatius)
|
30 |
|
31 |
## Training procedure
|
32 |
|
|
|
65 |
|
66 |
![Model Image](./model.png)
|
67 |
|
68 |
+
</details>
|
69 |
+
|
70 |
+
## Usage
|
71 |
+
|
72 |
+
The instance token used is "ignatius". A prompt example is as follows "a photo of ignatius on a car"
|
73 |
+
|
74 |
+
```python
|
75 |
+
from huggingface_hub import from_pretrained_keras
|
76 |
+
import keras_cv
|
77 |
+
|
78 |
+
sd_dreambooth_model = keras_cv.models.StableDiffusion(
|
79 |
+
img_width=resolution, img_height=resolution, jit_compile=True,
|
80 |
+
)
|
81 |
+
loaded_diffusion_model = from_pretrained_keras("keras-dreambooth/ignatius")
|
82 |
+
sd_dreambooth_model._diffusion_model = loaded_diffusion_model
|
83 |
+
|
84 |
+
prompt = f"ignatius on the moon"
|
85 |
+
|
86 |
+
#generated_img = sd_dreambooth_model.text_to_image(
|
87 |
+
generated_img = dreambooth_model.text_to_image(
|
88 |
+
prompt,
|
89 |
+
batch_size=4,
|
90 |
+
num_steps=150,
|
91 |
+
unconditional_guidance_scale=15,
|
92 |
+
)
|
93 |
+
```
|