Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,25 @@ If you want more details on how to generate your own blip cpationed dataset see
|
|
| 19 |
|
| 20 |
Training was done using a slightly modified version of Hugging-Face's text to image training [example script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py)
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
```py
|
| 23 |
from diffusers import StableDiffusionPipeline, LMSDiscreteScheduler
|
| 24 |
import torch
|
|
@@ -44,22 +63,6 @@ image = pipe(prompt).images[0]
|
|
| 44 |
image.save("astronaut_rides_horse.png")
|
| 45 |
```
|
| 46 |
|
| 47 |
-
## About
|
| 48 |
-
|
| 49 |
-
Put in a text prompt and generate cartoony/simpsony images
|
| 50 |
-
|
| 51 |
-
**A beautiful hungry demon girl, John Philip Falter, Very detailed painting, Mark Ryden**
|
| 52 |
-
|
| 53 |
-

|
| 54 |
-
|
| 55 |
-
**Gal Gadot, cartoon**
|
| 56 |
-
|
| 57 |
-

|
| 58 |
-
|
| 59 |
-
## More examples
|
| 60 |
-
|
| 61 |
-
The [examples](https://huggingface.co/Norod78/sd-simpsons-model/tree/main/examples) folder contains a few images generated by this model's ckpt file using [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) which means their EXIF info contain the parameter used to generate them
|
| 62 |
-
|
| 63 |
## Dataset and Training
|
| 64 |
|
| 65 |
Finetuned for 10,000 iterations upon [Runway ML's Stable-Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on [BLIP captioned Simpsons images](https://huggingface.co/datasets/Norod78/simpsons-blip-captions) using 1xA5000 GPU on my home desktop computer
|
|
|
|
| 19 |
|
| 20 |
Training was done using a slightly modified version of Hugging-Face's text to image training [example script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py)
|
| 21 |
|
| 22 |
+
## About
|
| 23 |
+
|
| 24 |
+
Put in a text prompt and generate cartoony/simpsony images
|
| 25 |
+
|
| 26 |
+
**A beautiful hungry demon girl, John Philip Falter, Very detailed painting, Mark Ryden**
|
| 27 |
+
|
| 28 |
+

|
| 29 |
+
|
| 30 |
+
**Gal Gadot, cartoon**
|
| 31 |
+
|
| 32 |
+

|
| 33 |
+
|
| 34 |
+
## More examples
|
| 35 |
+
|
| 36 |
+
The [examples](https://huggingface.co/Norod78/sd-simpsons-model/tree/main/examples) folder contains a few images generated by this model's ckpt file using [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) which means their EXIF info contain the parameter used to generate them
|
| 37 |
+
|
| 38 |
+
## Sample code
|
| 39 |
+
|
| 40 |
+
|
| 41 |
```py
|
| 42 |
from diffusers import StableDiffusionPipeline, LMSDiscreteScheduler
|
| 43 |
import torch
|
|
|
|
| 63 |
image.save("astronaut_rides_horse.png")
|
| 64 |
```
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
## Dataset and Training
|
| 67 |
|
| 68 |
Finetuned for 10,000 iterations upon [Runway ML's Stable-Diffusion v1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on [BLIP captioned Simpsons images](https://huggingface.co/datasets/Norod78/simpsons-blip-captions) using 1xA5000 GPU on my home desktop computer
|