Files changed (1) hide show
  1. README.md +7 -14
README.md CHANGED
@@ -8,30 +8,23 @@ tags:
8
  - diffusers
9
  ---
10
 
11
- # Plat Diffusion v1.2.1
12
 
13
- Plat Diffusion is a fine-tuned model based on [Waifu Diffusion v1.3](https://huggingface.co/hakurei/waifu-diffusion) with images generated with niji・journey.
 
 
14
 
15
- ![sunflower.png](https://s3.amazonaws.com/moonup/production/uploads/1671474750149-6305db1fcfbde33ef7d480ff.png)
16
 
17
  ```
18
- masterpiece, 1girl, flower, sunflower, solo, smile, earrings, shirt, jewelry, holding, blurry, bangs, petals, blush, long hair, looking at viewer, holding flower, brown hair, white shirt, collared shirt, yellow flower, blurry background, closed mouth, blue eyes, upper body, depth of field
19
  ```
20
 
21
  ### Recomended Negative Prompt
22
- Same as NAI's "Low Quality + Bad Anatomy"
23
 
24
  ```
25
- lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
26
  ```
27
 
28
- ## Special Tags
29
-
30
- In version 1.2.1, the following special tags can be used
31
-
32
- - masterpiece: high quality illustrations are classified as `masterpiece`.
33
-
34
-
35
 
36
  # 🧨 Diffusers
37
 
@@ -43,7 +36,7 @@ model_id = "p1atdev/plat-diffusion"
43
  pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
44
  pipe = pipe.to("cuda")
45
 
46
- prompt = "masterpiece, 1girl, surrounded by many flowers"
47
  image = pipe(prompt).images[0]
48
 
49
  image.save("girl.png")
 
8
  - diffusers
9
  ---
10
 
11
+ # Plat Diffusion v1.3.0
12
 
13
+ Plat Diffusion is a fine-tuned model based on [Waifu Diffusion v1.4 Anime Epoch 1](https://huggingface.co/hakurei/waifu-diffusion-v1-4) with images generated with niji・journey.
14
+
15
+ ![image.png](https://s3.amazonaws.com/moonup/production/uploads/1672836449977-6305db1fcfbde33ef7d480ff.png)
16
 
 
17
 
18
  ```
19
+ masterpiece, best quality, 1girl, orange feather, blue crystals, blurry foreground
20
  ```
21
 
22
  ### Recomended Negative Prompt
 
23
 
24
  ```
25
+ nsfw, worst quality, low quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
26
  ```
27
 
 
 
 
 
 
 
 
28
 
29
  # 🧨 Diffusers
30
 
 
36
  pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
37
  pipe = pipe.to("cuda")
38
 
39
+ prompt = "masterpiece, best quality, 1girl, orange feather, blue crystals, blurry foreground"
40
  image = pipe(prompt).images[0]
41
 
42
  image.save("girl.png")