Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,39 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
## Pony Diffusion XL Model Card
|
| 5 |
+
|
| 6 |
+
Pony Diffusion XL is a latent text-to-image diffusion model capable of generating images of Horses, mainly, and other things. For more information about how Stable Diffusion functions, please have a look at 🤗's [Stable Diffusion blog](https://huggingface.co/blog/stable_diffusion).
|
| 7 |
+
|
| 8 |
+
You can use this with the 🧨Diffusers library from [Hugging Face](https://huggingface.co).
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
### Diffusers
|
| 13 |
+
```py
|
| 14 |
+
from diffusers import StableDiffusionPipeline
|
| 15 |
+
import torch
|
| 16 |
+
|
| 17 |
+
pipeline = StableDiffusionPipeline.from_pretrained("nroggendorff/ponyxl").to("cuda")
|
| 18 |
+
|
| 19 |
+
image = pipeline(prompt="a chibi doll").images[0]
|
| 20 |
+
image.save("horse.png")
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
### Model Details
|
| 24 |
+
- `train_batch_size`: 1
|
| 25 |
+
- `gradient_accumulation_steps`: 4
|
| 26 |
+
- `learning_rate`: 1e-2
|
| 27 |
+
- `lr_warmup_steps`: 500
|
| 28 |
+
- `mixed_precision`: "fp16"
|
| 29 |
+
- `eval_metric`: "mean_squared_error"
|
| 30 |
+
|
| 31 |
+
### Limitations
|
| 32 |
+
|
| 33 |
+
- The model does not achieve perfect photorealism
|
| 34 |
+
- The model cannot render legible text
|
| 35 |
+
|
| 36 |
+
### Developed by
|
| 37 |
+
- Noa Linden Roggendorff
|
| 38 |
+
|
| 39 |
+
*This model card was written by Noa Roggendorff and is based on the [Stable Diffusion v1-5 Model Card](https://huggingface.co/runwayml/stable-diffusion-v1-5).*
|