Update README.md

#54
by bullbob - opened
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -8,7 +8,20 @@ license: creativeml-openrail-m
8
  inference: true
9
 
10
  ---
 
 
 
11
 
 
 
 
 
 
 
 
 
 
 
12
  # waifu-diffusion v1.3 - Diffusion for Weebs
13
 
14
  waifu-diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.
 
8
  inference: true
9
 
10
  ---
11
+ import torch
12
+ from torch import autocast
13
+ from diffusers import StableDiffusionPipeline
14
 
15
+ pipe = StableDiffusionPipeline.from_pretrained(
16
+ 'hakurei/waifu-diffusion',
17
+ torch_dtype=torch.float32
18
+ ).to('cuda')
19
+
20
+ prompt = "1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt"
21
+ with autocast("cuda"):
22
+ image = pipe(prompt, guidance_scale=6)["sample"][0]
23
+
24
+ image.save("test.png")
25
  # waifu-diffusion v1.3 - Diffusion for Weebs
26
 
27
  waifu-diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.