Panchovix commited on
Commit
528a099
1 Parent(s): b1bbeed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +171 -5
README.md CHANGED
@@ -1,5 +1,171 @@
1
- ---
2
- license: other
3
- license_name: other
4
- license_link: LICENSE
5
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: fair-ai-public-license-1.0-sd
4
+ license_link: https://freedevproject.org/faipl-1.0-sd/
5
+ language:
6
+ - en
7
+ base_model:
8
+ - Laxhar/noobai-XL-1.0
9
+ pipeline_tag: text-to-image
10
+ tags:
11
+ - Diffusers
12
+ - Safetensors
13
+ ---
14
+ Fix using similar method of NoobaiCyberFix (https://civitai.com/models/913998/noobaicyberfix?modelVersionId=1022962) but using the eps 1.1 model, while also doing it with perpendicular using sd_mecha, recipe from: https://huggingface.co/Doctor-Shotgun/NoobAI-XL-Merges
15
+
16
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/649608ca0b01497fb78e2e5c/JNmBFxW1yoZDf-hmaPf4r.jpeg)
17
+
18
+ <h1 align="center"><strong style="font-size: 48px;">NoobAI XL 1.1</strong></h1>
19
+
20
+ # New Image Generation Model
21
+
22
+ This is an image generation model based on training from Illustrious-xl.
23
+
24
+ It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption.
25
+
26
+ # Model Introduction
27
+
28
+ ## Model Details
29
+ - **Developed by**: [Laxhar Lab](https://huggingface.co/Laxhar)
30
+
31
+ - **Model Type**: Diffusion-based text-to-image generative model
32
+
33
+ - **Fine-tuned from**: Laxhar/noobai-XL-1.0
34
+
35
+ - **Sponsored by from**: [Lanyun Cloud](https://cloud.lanyun.net)
36
+
37
+ # Recommended Settings
38
+
39
+ ## Parameters
40
+ - CFG: 5 ~ 6
41
+ - Steps: 25 ~ 30
42
+ - Sampling Method:Euler a
43
+ - Resolution: Total area around 1024x1024. Best to choose from: 768x1344, **832x1216**, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768
44
+
45
+
46
+ ## Prompts
47
+
48
+ - Prompt Prefix:
49
+
50
+ ```
51
+ masterpiece, best quality, newest, absurdres, highres, safe,
52
+ ```
53
+
54
+ - Negative Prompt:
55
+
56
+ ```
57
+ nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro
58
+ ```
59
+
60
+ # Usage Guidelines
61
+
62
+ ## Caption
63
+
64
+ ```
65
+ <1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>, <other tags>
66
+ ```
67
+
68
+ ## Quality Tags
69
+
70
+ For quality tags, we evaluated image popularity through the following process:
71
+
72
+ - Data normalization based on various sources and ratings.
73
+ - Application of time-based decay coefficients according to date recency.
74
+ - Ranking of images within the entire dataset based on this processing.
75
+
76
+ Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years.
77
+
78
+ | Percentile Range | Quality Tags |
79
+ | :--------------- | :------------- |
80
+ | > 95th | masterpiece |
81
+ | > 85th, <= 95th | best quality |
82
+ | > 60th, <= 85th | good quality |
83
+ | > 30th, <= 60th | normal quality |
84
+ | <= 30th | worst quality |
85
+
86
+
87
+ ## Date tags
88
+ | Year Range | Period |
89
+ |:-----------------|:------------------|
90
+ | 2005-2010 | old |
91
+ | 2011-2014 | early |
92
+ | 2014-2017 | mid |
93
+ | 2018-2020 | recent |
94
+ | 2021-2024 | newest |
95
+
96
+ ## Datasets
97
+ - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23)
98
+ - E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face
99
+ -
100
+ **Communication**
101
+
102
+ - **QQ Groups:**
103
+
104
+ - 875042008
105
+ - 914818692
106
+ - 635772191
107
+
108
+ - **Discord:** [Laxhar Dream Lab SDXL NOOB](https://discord.com/invite/DKnFjKEEvH)
109
+
110
+ **Utility Tool**
111
+
112
+ Laxhar Lab is training a dedicated ControlNet model for NoobXL, and the models are being released progressively. So far, the normal, depth, and canny have been released.
113
+
114
+ Model link: https://civitai.com/models/929685
115
+
116
+ # Model License
117
+
118
+ This model's license inherits from https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0 fair-ai-public-license-1.0-sd and adds the following terms. Any use of this model and its variants is bound by this license.
119
+
120
+ ## I. Usage Restrictions
121
+
122
+ - Prohibited use for harmful, malicious, or illegal activities, including but not limited to harassment, threats, and spreading misinformation.
123
+ - Prohibited generation of unethical or offensive content.
124
+ - Prohibited violation of laws and regulations in the user's jurisdiction.
125
+
126
+ ## II. Commercial Prohibition
127
+
128
+ We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products.
129
+
130
+ ## III. Open Source Community
131
+
132
+ To foster a thriving open-source community,users MUST comply with the following requirements:
133
+
134
+ - Open source derivative models, merged models, LoRAs, and products based on the above models.
135
+ - Share work details such as synthesis formulas, prompts, and workflows.
136
+ - Follow the fair-ai-public-license to ensure derivative works remain open source.
137
+
138
+ ## IV. Disclaimer
139
+
140
+ Generated models may produce unexpected or harmful outputs. Users must assume all risks and potential consequences of usage.
141
+
142
+ # Participants and Contributors
143
+
144
+ ## Participants
145
+
146
+ - **L_A_X:** [Civitai](https://civitai.com/user/L_A_X) | [Liblib.art](https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69) | [Huggingface](https://huggingface.co/LAXMAYDAY)
147
+ - **li_li:** [Civitai](https://civitai.com/user/li_li) | [Huggingface](https://huggingface.co/heziiiii)
148
+ - **nebulae:** [Civitai](https://civitai.com/user/kitarz) | [Huggingface](https://huggingface.co/NebulaeWis)
149
+ - **Chenkin:** [Civitai](https://civitai.com/user/Chenkin) | [Huggingface](https://huggingface.co/windsingai)
150
+ - **Euge:** [Civitai](https://civitai.com/user/Euge_) | [Huggingface](https://huggingface.co/Eugeoter) | [Github](https://github.com/Eugeoter)
151
+
152
+ ## Contributors
153
+
154
+ - **Narugo1992**: Thanks to [narugo1992](https://github.com/narugo1992) and the [deepghs](https://huggingface.co/deepghs) team for open-sourcing various training sets, image processing tools, and models.
155
+
156
+ - **Mikubill**: Thanks to [Mikubill](https://github.com/Mikubill) for the [Naifu](https://github.com/Mikubill/naifu) trainer.
157
+
158
+ - **Onommai**: Thanks to [OnommAI](https://onomaai.com/) for open-sourcing a powerful base model.
159
+
160
+ - **V-Prediction**: Thanks to the following individuals for their detailed instructions and experiments.
161
+
162
+ - adsfssdf
163
+ - [bluvoll](https://civitai.com/user/bluvoll)
164
+ - [bvhari](https://github.com/bvhari)
165
+ - [catboxanon](https://github.com/catboxanon)
166
+ - [parsee-mizuhashi](https://huggingface.co/parsee-mizuhashi)
167
+ - [very-aesthetic](https://github.com/very-aesthetic)
168
+ - [momoura](https://civitai.com/user/momoura)
169
+ - madmanfourohfour
170
+
171
+ - **Community**: [aria1th261](https://civitai.com/user/aria1th261), [neggles](https://github.com/neggles/neurosis), [sdtana](https://huggingface.co/sdtana), [chewing](https://huggingface.co/chewing), [irldoggo](https://github.com/irldoggo), [reoe](https://huggingface.co/reoe), [kblueleaf](https://civitai.com/user/kblueleaf), [Yidhar](https://github.com/Yidhar), ageless, 白玲可, Creeper, KaerMorh, 吟游诗人, SeASnAkE, [zwh20081](https://civitai.com/user/zwh20081), Wenaka⁧~喵, 稀里哗啦, 幸运二副, 昨日の約, 445, [EBIX](https://civitai.com/user/EBIX), [Sopp](https://huggingface.co/goyishsoyish), [Y_X](https://civitai.com/user/Y_X), [Minthybasis](https://civitai.com/user/Minthybasis), [Rakosz](https://civitai.com/user/Rakosz)