Update README.md
Browse files
README.md
CHANGED
@@ -9,89 +9,22 @@ tags:
|
|
9 |
- diffusers
|
10 |
---
|
11 |
|
12 |
-
# Plat Diffusion v1.3.
|
13 |
|
14 |
-
Plat Diffusion is a fine-tuned
|
15 |
|
16 |
`.safetensors` file is [here](https://huggingface.co/p1atdev/pd-archive/tree/main).
|
17 |
|
18 |
[kl-f8-anime2.ckpt](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt) is recommended for VAE.
|
19 |
|
20 |
-
![thumbnail](https://bit.ly/3Is8sF8)
|
21 |
|
22 |
|
23 |
### Recomended Negative Prompt
|
24 |
|
25 |
```
|
26 |
-
nsfw, worst quality, low quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra
|
27 |
```
|
28 |
|
29 |
-
# Samples
|
30 |
-
|
31 |
-
- Autumn 1girl
|
32 |
-
|
33 |
-
![sample1](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample1.jpg)
|
34 |
-
|
35 |
-
```
|
36 |
-
masterpiece, best quality, 1girl, brown hair, long hair, green eyes, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden
|
37 |
-
Negative prompt: 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,
|
38 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
39 |
-
```
|
40 |
-
|
41 |
-
- Autumn 1boy
|
42 |
-
|
43 |
-
![sample2](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample2.jpg)
|
44 |
-
|
45 |
-
|
46 |
-
```
|
47 |
-
masterpiece, best quality, 1boy, solo, male focus, medium hair, blonde hair, blue eyes, autumn, cumulonimbus clouds, lighting, blue sky, falling leaves, garden
|
48 |
-
Negative prompt: 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,
|
49 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
50 |
-
```
|
51 |
-
|
52 |
-
- Abandoned city
|
53 |
-
|
54 |
-
![sample3](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample3.jpg)
|
55 |
-
|
56 |
-
|
57 |
-
```
|
58 |
-
masterpiece, best quality, scenery, abandoned city, buildings, ruins, rust, blue sky, clouds
|
59 |
-
Negative prompt: 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,
|
60 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
61 |
-
```
|
62 |
-
|
63 |
-
- Grey hair school uniform 1girl
|
64 |
-
|
65 |
-
![sample4](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample4.jpg)
|
66 |
-
|
67 |
-
|
68 |
-
```
|
69 |
-
masterpiece, best quality, 1girl, upper body, long hair, grey hair, grey eyes, curly hair, twintails, school uniform, black ribbon, light smile
|
70 |
-
Negative prompt: 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,
|
71 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
72 |
-
```
|
73 |
-
|
74 |
-
- 1girl with feathers
|
75 |
-
|
76 |
-
![sample5](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample5.jpg)
|
77 |
-
|
78 |
-
|
79 |
-
```
|
80 |
-
masterpiece, best quality, 1girl, angel, silver hair, white wings, hair flower, school uniform, upper body, sunlight, lily, feathers, ultra detailed illustration
|
81 |
-
Negative prompt: 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,
|
82 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
83 |
-
```
|
84 |
-
|
85 |
-
- Many girls
|
86 |
-
|
87 |
-
![sample6](https://huggingface.co/p1atdev/plat-diffusion/resolve/main/samples/sample6.jpg)
|
88 |
-
|
89 |
-
|
90 |
-
```
|
91 |
-
masterpiece, best quality, high quality, 4girls, everyone, beautiful detailed
|
92 |
-
Negative prompt: 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,
|
93 |
-
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7
|
94 |
-
```
|
95 |
|
96 |
|
97 |
# 🧨 Diffusers
|
@@ -104,8 +37,8 @@ model_id = "p1atdev/plat-diffusion"
|
|
104 |
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32) # not working with float16
|
105 |
pipe = pipe.to("cuda")
|
106 |
|
107 |
-
prompt = "masterpiece, best quality, 1girl,
|
108 |
-
negative_prompt = "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"
|
109 |
image = pipe(prompt, negative_prompt=negative_prompt).images[0]
|
110 |
|
111 |
image.save("girl.png")
|
|
|
9 |
- diffusers
|
10 |
---
|
11 |
|
12 |
+
# Plat Diffusion v1.3.1
|
13 |
|
14 |
+
Plat Diffusion v1.3.1 is a latent model fine-tuned on [Waifu Diffusion v1.4 Anime Epoch 2](https://huggingface.co/hakurei/waifu-diffusion-v1-4) with images from niji・journey.
|
15 |
|
16 |
`.safetensors` file is [here](https://huggingface.co/p1atdev/pd-archive/tree/main).
|
17 |
|
18 |
[kl-f8-anime2.ckpt](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt) is recommended for VAE.
|
19 |
|
|
|
20 |
|
21 |
|
22 |
### Recomended Negative Prompt
|
23 |
|
24 |
```
|
25 |
+
nsfw, worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digits, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
|
26 |
```
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
|
30 |
# 🧨 Diffusers
|
|
|
37 |
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32) # not working with float16
|
38 |
pipe = pipe.to("cuda")
|
39 |
|
40 |
+
prompt = "masterpiece, best quality, 1girl, solo, short hair, looking at viewer, japanese clothes, blue hair, portrait, kimono, bangs, colorful, closed mouth, blue kimono, butterfly, blue eyes, ultra detailed illustration"
|
41 |
+
negative_prompt = "nsfw, worst quality, low quality, medium quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry"
|
42 |
image = pipe(prompt, negative_prompt=negative_prompt).images[0]
|
43 |
|
44 |
image.save("girl.png")
|