Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- pytorch
|
| 5 |
+
- diffusers
|
| 6 |
+
- stable-diffusion
|
| 7 |
+
- text-to-image
|
| 8 |
+
- diffusion-models-class
|
| 9 |
+
- dreambooth-hackathon
|
| 10 |
+
- animal
|
| 11 |
+
widget:
|
| 12 |
+
- text: a photo of blofi fish in Times Square.
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
## Description
|
| 16 |
+
This is a Stable Diffusion model fine-tuned on the infamous blobfish (often remarked as the ugliest animal in the world) for the DreamBooth Hackathon 🔥 animal theme. To participate or learn more, visit [this page](https://huggingface.co/dreambooth-hackathon).
|
| 17 |
+
|
| 18 |
+
To generate blobfish images, use **a photo of blofi fish in [your choice]** or experiment with other variations. For some reason, GFC scale 5 seems to give the best results, at 7 images start get "overcooked". Despite multiple training runs with various settings, I couldn't fully solve this problem. Additional modifiers and negative prompts may also improve results.
|
| 19 |
+
|
| 20 |
+
## Examples
|
| 21 |
+
*a photo of blofi fish wearing a beautiful flower crown.*
|
| 22 |
+
|
| 23 |
+
*a photo of blofi fish in nerdy glasses.*
|
| 24 |
+
|
| 25 |
+
*a photo of blofi fish at the Arctic in a fluffy hat.*
|
| 26 |
+
|
| 27 |
+
*a photo of blofi fish in the Sahara desert.*
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Usage
|
| 32 |
+
|
| 33 |
+
```python
|
| 34 |
+
from diffusers import StableDiffusionPipeline
|
| 35 |
+
|
| 36 |
+
pipeline = StableDiffusionPipeline.from_pretrained('baruga/hideous-blobfish')
|
| 37 |
+
image = pipeline().images[0]
|
| 38 |
+
image
|
| 39 |
+
```
|