Update README.md
Browse files
README.md
CHANGED
@@ -19,3 +19,86 @@ tags:
|
|
19 |
- Not all features and/or results may be available in `CoreML` format.
|
20 |
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
|
21 |
- This model does not include a `safety checker` (for NSFW content).<br>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
- Not all features and/or results may be available in `CoreML` format.
|
20 |
- This model does not have the [unet split into chunks](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).
|
21 |
- This model does not include a `safety checker` (for NSFW content).<br>
|
22 |
+
|
23 |
+
# XXMix_9realistic-V2.6:
|
24 |
+
Source(s): [CivitAI](https://civitai.com/models/47274/xxmix9realistic)<br>
|
25 |
+
|
26 |
+
<img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c7facef9-b0ee-435c-9f7c-a8546f3749c5/width=450/13813-2748008393-(front focus),(in the dark_1.6),_Hyperrealist portrait of female by david hockney and alphonse mucha,fantasy ar.jpeg" alt="13813-2748008393-(front focus),(in the dark_1.6),_Hyperrealist portrait of female by david hockney and alphonse mucha,fantasy ar.png" style="max-height: 100%; max-width: 100%;">
|
27 |
+
<img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/86c85884-493f-4ac3-a3b1-da779b4d27b0/width=450/13814-1251401889-(in the dark_1.6),_Hyperrealist portrait of female by david hockney and alphonse mucha,fantasy art, photo reali.jpeg" alt="13814-1251401889-(in the dark_1.6),_Hyperrealist portrait of female by david hockney and alphonse mucha,fantasy art, photo reali.png" style="max-height: 100%; max-width: 100%;">
|
28 |
+
<img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8269e7b2-fe07-4503-b814-cca62296489a/width=450/22109-2099671408-headshot of Skeletal Zombie queen wearing an ornate crown and detailed plate armor, volumetric light,.jpeg" alt="22109-2099671408-headshot of Skeletal Zombie queen wearing an ornate crown and detailed plate armor, volumetric light,.png" style="max-height: 100%; max-width: 100%;">
|
29 |
+
<img class="mantine-7aj0so" src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6e51001c-b3dd-4734-9f6a-0e2c44f3781b/width=450/26638-2995801549-(absurdres, highres, ultra detailed), 1girl, solo, mature, (long beige hair), Baroque, dress, long sleeve, eleg.jpeg" alt="26638-2995801549-(absurdres, highres, ultra detailed), 1girl, solo, mature, (long beige hair), Baroque, dress, long sleeve, eleg.png" style="max-height: 100%; max-width: 100%;">
|
30 |
+
|
31 |
+
|
32 |
+
v26-fp16-no-ema update
|
33 |
+
|
34 |
+
------------------------------------------------------------------------------------------------------
|
35 |
+
|
36 |
+
v2.6版本说明:
|
37 |
+
|
38 |
+
这版算小更新,优化了脸型,手的问题有优化,不过主要还是抽卡。大问题下个版本解决。
|
39 |
+
|
40 |
+
Version 2.6 release notes:
|
41 |
+
|
42 |
+
This version is a minor update that optimizes the face and hand issues. However, the main focus is still on the gacha system. The major issues will be addressed in the next version.
|
43 |
+
|
44 |
+
------------------------------------------------------------------------------------------------------
|
45 |
+
|
46 |
+
有人留言说模型基本不能用,麻烦新朋友看下自己的设置是否和图例的设置一样,除了全身图会有IMG2IMG放大的操作,其他图都是直出的。请一定先确定自己设置是否和图里一样哈!!!
|
47 |
+
|
48 |
+
V2.5版本的光影效果表现更好,支持更多幻想内容,调整了基础脸型,场景方面的表现更好。
|
49 |
+
|
50 |
+
V2.5 version has better lighting effects and supports more fantasy content. The basic face shape has been adjusted, and the performance in scenes has been improved.
|
51 |
+
|
52 |
+
------------------------------------------------------------------------------------------------------
|
53 |
+
|
54 |
+
适当调小(CFG Scale)的数值,可以得到与众不同的效果。
|
55 |
+
|
56 |
+
V2版本说明:
|
57 |
+
|
58 |
+
1.更换了默认脸。
|
59 |
+
|
60 |
+
2.更好的光影表现。
|
61 |
+
|
62 |
+
3.融合了更多模型,后面还会继续迭代。
|
63 |
+
|
64 |
+
4.如果想得到更好的皮肤质感,那么生成图片的时候不要开启高清修复,而是将生成的图片传入图生图模式,启用Tiled Diffusion,来进行放大,从而得到更真实的皮肤质感。
|
65 |
+
|
66 |
+
5.我会继续更新迭代这个大模型,希望能不断填充内容,让模型更具趣味性。
|
67 |
+
|
68 |
+
谢谢您的支持!
|
69 |
+
|
70 |
+
Version 2 Release Notes:
|
71 |
+
|
72 |
+
Changed the default face.
|
73 |
+
|
74 |
+
Improved lighting and shadow effects.
|
75 |
+
|
76 |
+
Added more models and will continue to iterate in the future.
|
77 |
+
|
78 |
+
For better skin texture, do not enable Hires Fix when generating images. Instead, use the "Tiled Diffusion" mode to enlarge the generated image and achieve a more realistic skin texture.
|
79 |
+
|
80 |
+
I will continue to update and iterate on this large model, hoping to add more content and make it more interesting.
|
81 |
+
|
82 |
+
Thank you for your support!
|
83 |
+
|
84 |
+
------------------------------------------------------------------------------------------------------
|
85 |
+
|
86 |
+
推荐参数
|
87 |
+
|
88 |
+
Recommended Parameters:
|
89 |
+
|
90 |
+
Sampler: DPM++ 2M Karras alt Karras or DPM++ SDE Karras
|
91 |
+
|
92 |
+
Steps: 20~40
|
93 |
+
|
94 |
+
Hires upscaler:4x-UltraSharp
|
95 |
+
|
96 |
+
Hires upscale: 2
|
97 |
+
|
98 |
+
Hires steps: 15
|
99 |
+
|
100 |
+
Denoising strength: 0.2~0.5
|
101 |
+
|
102 |
+
CFG scale: 6-8
|
103 |
+
|
104 |
+
clip skip 2
|