Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
datasets:
|
4 |
+
- foldl/rumeme-desc
|
5 |
+
language:
|
6 |
+
- ru
|
7 |
+
library_name: diffusers
|
8 |
+
pipeline_tag: text-to-image
|
9 |
+
---
|
10 |
+
|
11 |
+
# ruMeme Description model
|
12 |
+
|
13 |
+
|
14 |
+
## Example
|
15 |
+
|
16 |
+
*Use `Diffusers` >=0.8.0, do not support lower versions.*
|
17 |
+
|
18 |
+
```python
|
19 |
+
from diffusers import StableDiffusionPipeline
|
20 |
+
import torch
|
21 |
+
|
22 |
+
model_path = "foldl/sd-rumeme-desc"
|
23 |
+
pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
|
24 |
+
pipe.to("cuda")
|
25 |
+
|
26 |
+
image = pipe(prompt="кот").images[0]
|
27 |
+
image.save("cat".jpg)
|
28 |
+
```
|
29 |
+
|
30 |
+
## Training
|
31 |
+
|
32 |
+
### Training Procedure
|
33 |
+
|
34 |
+
Model was trained on 1 P100 GPU.
|
35 |
+
|
36 |
+
Base model - https://huggingface.co/OFA-Sys/small-stable-diffusion-v0
|
37 |
+
|
38 |
+
### Training Data
|
39 |
+
- https://huggingface.co/datasets/foldl/rumeme-desc
|