NebulaeWis commited on
Commit
a4fd004
1 Parent(s): fbcf927

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -57
README.md CHANGED
@@ -29,55 +29,55 @@ It utilizes the latest full Danbooru and e621 datasets for training, with native
29
 
30
  - **Sponsored by from**: [Lanyun Cloud](https://cloud.lanyun.net)
31
 
32
- **Communication**
33
-
34
- * **QQ Groups:**
35
- * 875042008
36
- * 914818692
37
- * 635772191
38
-
39
- * **Discord:** [Laxhar Dream Lab SDXL NOOB](https://discord.com/invite/DKnFjKEEvH)
40
-
41
-
42
  # Recommended Settings
43
 
44
  ## Parameters
45
  - CFG: 5 ~ 6
46
  - Steps: 25 ~ 30
47
  - Sampling Method:Euler a
48
- - Resolution:aim for around 1024\*1024
 
 
49
  ## Prompts
50
- - Prompt:
 
 
51
  ```
52
  masterpiece, best quality, newest, absurdres, highres, safe,
53
  ```
 
54
  - Negative Prompt:
 
55
  ```
56
- nsfw,worst quality,old,early,low quality,quality,lowres,signature,username,bad id,bad twitter id,english commentary,logo,bad hands,mutated hands,mammal,anthro,furry,ambiguous_form,feral,semi-anthro
57
  ```
58
 
59
  # Usage Guidelines
60
 
61
  ## Caption
62
- ```
63
- <1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>, <other tags>
64
- ```
 
65
 
66
  ## Quality Tags
67
- For quality tags, we evaluated image popularity through the following process:
68
- - Data normalization based on various sources and ratings.
69
- - Application of time-based decay coefficients according to date recency.
70
- - Ranking of images within the entire dataset based on this processing.
71
-
 
 
72
  Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years.
73
 
74
- | Percentile Range | Quality Tags |
75
- |:-----------------|:------------------|
76
- | > 95th | masterpiece |
77
- | > 85th, <= 95th | best quality |
78
- | > 60th, <= 85th | good quality |
79
- | > 30th, <= 60th | normal quality |
80
- | <= 30th | worst quality |
 
81
 
82
  ## Date tags
83
  | Year Range | Period |
@@ -91,10 +91,26 @@ Our ultimate goal is to ensure that quality tags effectively track user preferen
91
  ## Datasets
92
  - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23)
93
  - E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
 
95
  # Model License
96
 
97
- 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.
98
 
99
  ## I. Usage Restrictions
100
 
@@ -108,7 +124,7 @@ We prohibit any form of commercialization, including but not limited to monetiza
108
 
109
  ## III. Open Source Community
110
 
111
- For the open source community, you need to:
112
 
113
  - Open source derivative models, merged models, LoRAs, and products based on the above models.
114
  - Share work details such as synthesis formulas, prompts, and workflows.
@@ -122,33 +138,29 @@ Generated models may produce unexpected or harmful outputs. Users must assume al
122
 
123
  ## Participants
124
 
125
- * **L_A_X:** [Civitai](https://civitai.com/user/L_A_X) | [Liblib.art](https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69)
126
- * **li_li:** [Civitai](https://civitai.com/user/li_li)
127
- * **nebulae:** [Civitai](https://civitai.com/user/kitarz)
128
- * **Chenkin:** [Civitai](https://civitai.com/user/Chenkin)
129
- * **Euge:** [Civitai](https://civitai.com/user/Euge_)
130
-
131
 
132
  ## Contributors
133
 
134
- * **Narugo1992:** Thanks to narugo1992 and the deepghs team for open-sourcing various training sets, image processing tools, and models.
135
- * [GitHub](https://github.com/narugo1992)
136
- * [Hugging Face](https://huggingface.co/deepghs)
137
-
138
- * **Naifu:** Training scripts
139
- * [GitHub](https://github.com/Mikubill/naifu)
140
-
141
- * **Onommai:** Thanks to onommai for open-sourcing a powerful base model.
142
- * [Onommai](https://onomaai.com/)
143
-
144
- * **aria1th261:** [Civitai](https://civitai.com/user/aria1th261)
145
- * **neggles:** [GitHub](https://github.com/neggles/neurosis)
146
- * **parsee-mizuhashi:** [Hugging Face](https://huggingface.co/parsee-mizuhashi)
147
- * **bluvoll:** [Civitai](https://civitai.com/user/bluvoll)
148
- * **sdtana:** [Hugging Face](https://huggingface.co/sdtana)
149
- * **chewing:** [Hugging Face](https://huggingface.co/chewing)
150
- * **irldoggo:** [GitHub](https://github.com/irldoggo)
151
- * **reoe:** [Hugging Face](https://huggingface.co/reoe)
152
- * **kblueleaf:** [Civitai](https://civitai.com/user/kblueleaf)
153
- * **Yidhar:** [GitHub](https://github.com/Yidhar)
154
- * **Others:** 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), adsfssdf, [Minthybasis](https://civitai.com/user/Minthybasis), [Rakosz](https://civitai.com/user/Rakosz)
 
29
 
30
  - **Sponsored by from**: [Lanyun Cloud](https://cloud.lanyun.net)
31
 
 
 
 
 
 
 
 
 
 
 
32
  # Recommended Settings
33
 
34
  ## Parameters
35
  - CFG: 5 ~ 6
36
  - Steps: 25 ~ 30
37
  - Sampling Method:Euler a
38
+ - Resolution: Total area around 1024x1024. Best to choose from: 768x1344, **832x1216**, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768
39
+
40
+
41
  ## Prompts
42
+
43
+ - Prompt Prefix:
44
+
45
  ```
46
  masterpiece, best quality, newest, absurdres, highres, safe,
47
  ```
48
+
49
  - Negative Prompt:
50
+
51
  ```
52
+ nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro
53
  ```
54
 
55
  # Usage Guidelines
56
 
57
  ## Caption
58
+
59
+ ```
60
+ <1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>, <other tags>
61
+ ```
62
 
63
  ## Quality Tags
64
+
65
+ For quality tags, we evaluated image popularity through the following process:
66
+
67
+ - Data normalization based on various sources and ratings.
68
+ - Application of time-based decay coefficients according to date recency.
69
+ - Ranking of images within the entire dataset based on this processing.
70
+
71
  Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years.
72
 
73
+ | Percentile Range | Quality Tags |
74
+ | :--------------- | :------------- |
75
+ | > 95th | masterpiece |
76
+ | > 85th, <= 95th | best quality |
77
+ | > 60th, <= 85th | good quality |
78
+ | > 30th, <= 60th | normal quality |
79
+ | <= 30th | worst quality |
80
+
81
 
82
  ## Date tags
83
  | Year Range | Period |
 
91
  ## Datasets
92
  - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23)
93
  - E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face
94
+ -
95
+ **Communication**
96
+
97
+ - **QQ Groups:**
98
+
99
+ - 875042008
100
+ - 914818692
101
+ - 635772191
102
+
103
+ - **Discord:** [Laxhar Dream Lab SDXL NOOB](https://discord.com/invite/DKnFjKEEvH)
104
+
105
+ **Utility Tool**
106
+
107
+ 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.
108
+
109
+ Model link: https://civitai.com/models/929685
110
 
111
  # Model License
112
 
113
+ 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.
114
 
115
  ## I. Usage Restrictions
116
 
 
124
 
125
  ## III. Open Source Community
126
 
127
+ To foster a thriving open-source community,users MUST comply with the following requirements:
128
 
129
  - Open source derivative models, merged models, LoRAs, and products based on the above models.
130
  - Share work details such as synthesis formulas, prompts, and workflows.
 
138
 
139
  ## Participants
140
 
141
+ - **L_A_X:** [Civitai](https://civitai.com/user/L_A_X) | [Liblib.art](https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69) | [Huggingface](https://huggingface.co/LAXMAYDAY)
142
+ - **li_li:** [Civitai](https://civitai.com/user/li_li) | [Huggingface](https://huggingface.co/heziiiii)
143
+ - **nebulae:** [Civitai](https://civitai.com/user/kitarz) | [Huggingface](https://huggingface.co/NebulaeWis)
144
+ - **Chenkin:** [Civitai](https://civitai.com/user/Chenkin) | [Huggingface](https://huggingface.co/windsingai)
145
+ - **Euge:** [Civitai](https://civitai.com/user/Euge_) | [Huggingface](https://huggingface.co/Eugeoter) | [Github](https://github.com/Eugeoter)
 
146
 
147
  ## Contributors
148
 
149
+ - **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.
150
+
151
+ - **Mikubill**: Thanks to [Mikubill](https://github.com/Mikubill) for the [Naifu](https://github.com/Mikubill/naifu) trainer.
152
+
153
+ - **Onommai**: Thanks to [OnommAI](https://onomaai.com/) for open-sourcing a powerful base model.
154
+
155
+ - **V-Prediction**: Thanks to the following individuals for their detailed instructions and experiments.
156
+
157
+ - adsfssdf
158
+ - [bluvoll](https://civitai.com/user/bluvoll)
159
+ - [bvhari](https://github.com/bvhari)
160
+ - [catboxanon](https://github.com/catboxanon)
161
+ - [parsee-mizuhashi](https://huggingface.co/parsee-mizuhashi)
162
+ - [very-aesthetic](https://github.com/very-aesthetic)
163
+ - [momoura](https://civitai.com/user/momoura)
164
+ - madmanfourohfour
165
+
166
+ - **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)