Upload README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,114 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
+
tags:
|
4 |
+
- coreml
|
5 |
+
- stable-diffusion
|
6 |
+
- text-to-image
|
7 |
---
|
8 |
+
# Core ML Converted Model:
|
9 |
+
|
10 |
+
- This model was converted to [Core ML for use on Apple Silicon devices](https://github.com/apple/ml-stable-diffusion). Conversion instructions can be found [here](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-ckpt-or-safetensors-files-to-Core-ML).
|
11 |
+
- Provide the model to an app such as **Mochi Diffusion** [Github](https://github.com/godly-devotion/MochiDiffusion) / [Discord](https://discord.gg/x2kartzxGv) to generate images.
|
12 |
+
- `split_einsum` version is compatible with all compute unit options including Neural Engine.
|
13 |
+
- `original` version is only compatible with `CPU & GPU` option.
|
14 |
+
- Custom resolution versions are tagged accordingly.
|
15 |
+
- The `vae-ft-mse-840000-ema-pruned.ckpt` VAE is embedded into the model.
|
16 |
+
- This model was converted with a `vae-encoder` for use with `image2image`.
|
17 |
+
- This model is `fp16`.
|
18 |
+
- Descriptions are posted as-is from original model source.
|
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).
|
22 |
+
- This model can be used with ControlNet.
|
23 |
+
|
24 |
+
<br>
|
25 |
+
|
26 |
+
# sweetMix-fp16-v21_cn:
|
27 |
+
Source(s): [CivitAI](https://civitai.com/models/18927?modelVersionId=106822)<br>
|
28 |
+
|
29 |
+
## Sweet-mix v2.1 FP16 VAE
|
30 |
+
|
31 |
+
Sweet-mix is the spritual succesor to my older model Colorful-Plus.
|
32 |
+
|
33 |
+
What sweet-mix improves compared to my older model is probably everything. Seriously, check it out. I think it's really neat.
|
34 |
+
|
35 |
+
MUST-HAVES FOR GREAT IMAGE GENERATION LIKE IN THE SAMPLE IMAGES:
|
36 |
+
|
37 |
+
This negative prompt: extra fingers, fewer fingers, bad-hands-5, by bad-artist, (bad eyes:1.2), (misfigured pupils:1.2), (bad clothing:1.3), (undetailed clothing:1.3), ng_deepnegative_v1_75t, verybadimagenegative_v1.3, (nonsensical backrounds:1.2), (bad backrounds:1.2), (bad shadows:1.2), (bad anatomy:1.1)
|
38 |
+
|
39 |
+
These textual inversions:
|
40 |
+
|
41 |
+
- bad-artist (Not the anime version)
|
42 |
+
|
43 |
+
- bad-hands5
|
44 |
+
|
45 |
+
- deep-negative
|
46 |
+
|
47 |
+
- verybadimagenegative
|
48 |
+
|
49 |
+
VAE
|
50 |
+
|
51 |
+
Clip skip: 2
|
52 |
+
|
53 |
+
And a great imagination :)
|
54 |
+
|
55 |
+
[Tensor.art link](https://tensor.art/models/609298835568805343) - free online generation
|
56 |
+
|
57 |
+
## Models that went into this merge:
|
58 |
+
|
59 |
+
Normal line-up:
|
60 |
+
|
61 |
+
Anything-v4.5
|
62 |
+
|
63 |
+
AbyssOrangeMix 3
|
64 |
+
|
65 |
+
Protogen
|
66 |
+
|
67 |
+
CitrineDreamMix (probably)
|
68 |
+
|
69 |
+
Peachmixs
|
70 |
+
|
71 |
+
Sardonyx-Blend (introduced in v1.1)
|
72 |
+
|
73 |
+
Meinahentai (introduced in v1.2)
|
74 |
+
|
75 |
+
IvoryOrangemix (introduced in v1.3)
|
76 |
+
|
77 |
+
MixPROV4 (introduced in v1.4)
|
78 |
+
|
79 |
+
Daintymixhentaimodel (introduced in v1.4)
|
80 |
+
|
81 |
+
Jasminiquemix (introduced in v1.5)
|
82 |
+
|
83 |
+
Sirenmix (introduced in v1.6)
|
84 |
+
|
85 |
+
bbmixluci (introduced in v1.6)
|
86 |
+
|
87 |
+
Sardonyx-Blend Redux (introduced in v1.6)
|
88 |
+
|
89 |
+
IceRealistic (introduced in v1.6)
|
90 |
+
|
91 |
+
Another blend i made consisting of multiple nsfw models (introduced in v1.7)
|
92 |
+
|
93 |
+
Calico Mix (introduced in v1.9)
|
94 |
+
|
95 |
+
Baka diffusion (introduced in v2.1)
|
96 |
+
|
97 |
+
Flat line-up:
|
98 |
+
|
99 |
+
Sweet-mix v1.7 (introduced in v1.8-flat)
|
100 |
+
|
101 |
+
ACMAR G Mix (introduced in v1.8-flat)
|
102 |
+
|
103 |
+
GOTTA MIX (introduced in v1.8-flat)
|
104 |
+
|
105 |
+
Anylora screencap (introduced in v2.0-flat)<br><br>
|
106 |
+
|
107 |
+
|
108 |
+
![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a0f8933f-60e2-4755-8551-e104214c03ff/width=450/00006-1940306026-blue_sky,%20building,%20bush,%20cliff,%20cloud,%20cloudy_sky,%20day,%20forest,%20grass,%20horizon,%20house,%20jungle,%20lake,%20lens_flare,%20light_rays,%20mo.jpeg)
|
109 |
+
|
110 |
+
![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e7156e27-6369-4678-9c87-9a16c574cc9a/width=450/00081-4193132894-Woman,%20balcony,%20cloud,%20cloudy_sky,%20constellation,%20constellation_print,%20crescent_moon,%20galaxy,%20gradient_sky,%20horizon,%20house,%20isla.jpeg)
|
111 |
+
|
112 |
+
![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b8b6ae10-914f-4b00-a308-522b4596ac3f/width=450/0082-1329824298-masterpiece,%20best%20quality,%20ultra-detailed,%20beautiful%20lighting,%20beautiful%20forest,%20colorful,%20Incredible%20view,%20lake,%20woman,%20swimmi.jpeg)
|
113 |
+
|
114 |
+
![image](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a222f7d5-2df7-4671-b421-4b1e5ade9e00/width=450/00083-2578633952-masterpiece,%20best%20quality,%20princess,%20(blue%20dress_1.2),%20blue%20eyes,%20blonde%20hair,%20standing,%20(castle_1.2),%20clouds,%20trees,%20arms%20behin.jpegg)
|