p1atdev commited on
Commit
49647d1
1 Parent(s): b8e6089

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -1
README.md CHANGED
@@ -9,4 +9,66 @@ tags:
9
  - stable-diffusion
10
  - safetensors
11
  - text-to-image
12
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  - stable-diffusion
10
  - safetensors
11
  - text-to-image
12
+ ---
13
+
14
+ # PVC v4
15
+
16
+ This model is a latent diffusion model finetuned on Waifu Diffusion v1.5 beta 2.6 with PVC figure images. You can use Danbooru tags to generate images.
17
+
18
+ ## Downloads
19
+
20
+ <div class="flex flex-col dark:bg-gray-900 rounded-md divide-y dark:divide-gray-800">
21
+
22
+ <div class="flex justify-between px-4 py-2">
23
+ <a class="underline" href="https://huggingface.co/p1atdev/pvc-v4/resolve/checkpoints/pvc-v4-fp16.safetensors">pvc-v4-fp16.safetensors</a>
24
+ <div>2.58 GB</div>
25
+ </div>
26
+
27
+ <div class="flex justify-between px-4 py-2">
28
+ <a class="underline" href="https://huggingface.co/p1atdev/pvc-v4/resolve/checkpoints/pvc-v4-fp32.safetensors">pvc-v4-fp32.safetensors</a>
29
+ <div>4.31 GB</div>
30
+ </div>
31
+
32
+
33
+ <div class="flex justify-between px-4 py-1">
34
+ <a class="underline opacity-75" href="https://huggingface.co/p1atdev/pvc-v4/tree/checkpoints">Show all</a>
35
+ </div>
36
+
37
+ </div>
38
+
39
+ Please use [WD's vae](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt) to get good results!
40
+
41
+ ## Prompt guide
42
+
43
+ ### Trigger words
44
+
45
+ - `pvc` means the pvc material style but not needed always.
46
+
47
+ - `figma` is the figure style that has joints, and more tend to be product thumbnail images. To get joints, please emphasize `figma` by 1.2 ~ 1.5.
48
+
49
+ - `nendoroid` means the style of chibi figures. Use with `chibi` to get better chibis.
50
+
51
+ ### Negative prompt
52
+
53
+ ```
54
+ (worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, cropped, signature, blurry
55
+ ```
56
+
57
+ ## Comparison
58
+
59
+ ![sample-diff-1]()
60
+
61
+ ```
62
+ masterpiece, best quality, best aesthetic, 1girl, red hair, cat ears, closed eyes, closed mouth, expressionless, maid costume, apron, lolita dress, frills, lying on back, sheets, red flowers, from above
63
+ Negative prompt: (worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, error, cropped, jpeg artifacts, signature, watermark, username, blurry
64
+ Steps: 18, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1166304922, Size: 512x768, Model hash: 0866b17d46, Model: pvc-v3-fp16, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires steps: 12, Hires upscaler: Latent
65
+ ```
66
+
67
+ ## Examples
68
+
69
+
70
+
71
+ ## License
72
+ This model is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.
73
+
74
+ WD1.5 と同じ Fiar AI Public License 1.0-SD ライセンスです。生成サービスなどでこのモデルまたは派生モデルを使う場合は、サービスの利用者にモデルを公開する必要があります。詳しい/正確なライセンスは [原文](https://freedevproject.org/faipl-1.0-sd/) を参照ください。