Add 🧨Diffusers library guide
Browse files
README.md
CHANGED
@@ -29,6 +29,28 @@ tags:
|
|
29 |
- **Sampling method, sampling steps and CFG scale**: I find **(Euler a, 28, 5)** good. You are encouraged to experiment with other settings.
|
30 |
- **Width and height**: **832*1216** for portrait, **1024*1024** for square, and **1216*832** for landscape.
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
## Training Details
|
33 |
|
34 |
AnimeBoysXL is trained from [Stable Diffusion XL Base 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), on ~516k images.
|
|
|
29 |
- **Sampling method, sampling steps and CFG scale**: I find **(Euler a, 28, 5)** good. You are encouraged to experiment with other settings.
|
30 |
- **Width and height**: **832*1216** for portrait, **1024*1024** for square, and **1216*832** for landscape.
|
31 |
|
32 |
+
## How to use from the 🧨Diffusers library
|
33 |
+
|
34 |
+
```python
|
35 |
+
import torch
|
36 |
+
from diffusers import DiffusionPipeline
|
37 |
+
|
38 |
+
pipe = DiffusionPipeline.from_pretrained("Koolchh/AnimeBoysXL-v1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
|
39 |
+
pipe.to("cuda")
|
40 |
+
|
41 |
+
prompt = ", best quality, amazing quality, best aesthetic, absurdres"
|
42 |
+
negative_prompt = "lowres, (bad:1.05), text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts, 1girl, breasts"
|
43 |
+
|
44 |
+
image = pipe(
|
45 |
+
prompt=prompt,
|
46 |
+
negative_prompt=negative_prompt,
|
47 |
+
width=1024,
|
48 |
+
height=1024,
|
49 |
+
guidance_scale=5,
|
50 |
+
num_inference_steps=28
|
51 |
+
).images[0]
|
52 |
+
```
|
53 |
+
|
54 |
## Training Details
|
55 |
|
56 |
AnimeBoysXL is trained from [Stable Diffusion XL Base 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), on ~516k images.
|