README.md
| 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 | - not-for-all-audiences |
| 14 | --- |
| 15 | |
| 16 | <h1 align="center"><strong style="font-size: 48px;">NoobAI XL 1.1</strong></h1> |
| 17 | |
| 18 | |
| 19 | # New Image Generation Model |
| 20 | |
| 21 | This is an image generation model based on training from Illustrious-xl. |
| 22 | |
| 23 | It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption. |
| 24 | |
| 25 | # Model Introduction |
| 26 | |
| 27 | ## Model Details |
| 28 | - **Developed by**: [Laxhar Lab](https://huggingface.co/Laxhar) |
| 29 | |
| 30 | - **Model Type**: Diffusion-based text-to-image generative model |
| 31 | |
| 32 | - **Fine-tuned from**: Laxhar/noobai-XL-1.0 |
| 33 | |
| 34 | - **Sponsored by from**: [Lanyun Cloud](https://cloud.lanyun.net) |
| 35 | |
| 36 | # Recommended Settings |
| 37 | |
| 38 | ## Parameters |
| 39 | - CFG: 5 ~ 6 |
| 40 | - Steps: 25 ~ 30 |
| 41 | - Sampling Method:Euler a |
| 42 | - Resolution: Total area around 1024x1024. Best to choose from: 768x1344, **832x1216**, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768 |
| 43 | |
| 44 | |
| 45 | ## Prompts |
| 46 | |
| 47 | - Prompt Prefix: |
| 48 | |
| 49 | ``` |
| 50 | masterpiece, best quality, newest, absurdres, highres, safe, |
| 51 | ``` |
| 52 | |
| 53 | - Negative Prompt: |
| 54 | |
| 55 | ``` |
| 56 | nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro |
| 57 | ``` |
| 58 | |
| 59 | # Usage Guidelines |
| 60 | |
| 61 | ## Caption |
| 62 | |
| 63 | ``` |
| 64 | <1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>, <other tags> |
| 65 | ``` |
| 66 | |
| 67 | ## Quality Tags |
| 68 | |
| 69 | For quality tags, we evaluated image popularity through the following process: |
| 70 | |
| 71 | - Data normalization based on various sources and ratings. |
| 72 | - Application of time-based decay coefficients according to date recency. |
| 73 | - Ranking of images within the entire dataset based on this processing. |
| 74 | |
| 75 | Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years. |
| 76 | |
| 77 | | Percentile Range | Quality Tags | |
| 78 | | :--------------- | :------------- | |
| 79 | | > 95th | masterpiece | |
| 80 | | > 85th, <= 95th | best quality | |
| 81 | | > 60th, <= 85th | good quality | |
| 82 | | > 30th, <= 60th | normal quality | |
| 83 | | <= 30th | worst quality | |
| 84 | |
| 85 | |
| 86 | ## Date tags |
| 87 | | Year Range | Period | |
| 88 | |:-----------------|:------------------| |
| 89 | | 2005-2010 | old | |
| 90 | | 2011-2014 | early | |
| 91 | | 2014-2017 | mid | |
| 92 | | 2018-2020 | recent | |
| 93 | | 2021-2024 | newest | |
| 94 | |
| 95 | ## Datasets |
| 96 | - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23) |
| 97 | - E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face |
| 98 | - |
| 99 | **Communication** |
| 100 | |
| 101 | - **QQ Groups:** |
| 102 | |
| 103 | - 427280545 |
| 104 | - 677964513 |
| 105 | - 852429527 |
| 106 | - 914818692 |
| 107 | - 635772191 |
| 108 | - 870086562 |
| 109 | |
| 110 | - **Discord:** [Laxhar Dream Lab SDXL NOOB](https://discord.com/invite/DKnFjKEEvH) |
| 111 | |
| 112 | **Utility Tool** |
| 113 | |
| 114 | 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. |
| 115 | |
| 116 | Model link: https://civitai.com/models/929685 |
| 117 | |
| 118 | # Model License |
| 119 | |
| 120 | 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. |
| 121 | |
| 122 | ## I. Usage Restrictions |
| 123 | |
| 124 | - Prohibited use for harmful, malicious, or illegal activities, including but not limited to harassment, threats, and spreading misinformation. |
| 125 | - Prohibited generation of unethical or offensive content. |
| 126 | - Prohibited violation of laws and regulations in the user's jurisdiction. |
| 127 | |
| 128 | ## II. Commercial Prohibition |
| 129 | |
| 130 | We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products. |
| 131 | |
| 132 | ## III. Open Source Community |
| 133 | |
| 134 | To foster a thriving open-source community,users MUST comply with the following requirements: |
| 135 | |
| 136 | - Open source derivative models, merged models, LoRAs, and products based on the above models. |
| 137 | - Share work details such as synthesis formulas, prompts, and workflows. |
| 138 | - Follow the fair-ai-public-license to ensure derivative works remain open source. |
| 139 | |
| 140 | ## IV. Disclaimer |
| 141 | |
| 142 | Generated models may produce unexpected or harmful outputs. Users must assume all risks and potential consequences of usage. |
| 143 | |
| 144 | # Participants and Contributors |
| 145 | |
| 146 | ## Participants |
| 147 | |
| 148 | - **L_A_X:** [Civitai](https://civitai.com/user/L_A_X) | [Liblib.art](https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69) | [Huggingface](https://huggingface.co/LAXMAYDAY) |
| 149 | - **li_li:** [Civitai](https://civitai.com/user/li_li) | [Huggingface](https://huggingface.co/heziiiii) |
| 150 | - **nebulae:** [Civitai](https://civitai.com/user/kitarz) | [Huggingface](https://huggingface.co/NebulaeWis) |
| 151 | - **Chenkin:** [Civitai](https://civitai.com/user/Chenkin) | [Huggingface](https://huggingface.co/windsingai) |
| 152 | - **Euge:** [Civitai](https://civitai.com/user/Euge_) | [Huggingface](https://huggingface.co/Eugeoter) | [Github](https://github.com/Eugeoter) |
| 153 | |
| 154 | ## Contributors |
| 155 | |
| 156 | - **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. |
| 157 | |
| 158 | - **Mikubill**: Thanks to [Mikubill](https://github.com/Mikubill) for the [Naifu](https://github.com/Mikubill/naifu) trainer. |
| 159 | |
| 160 | - **Onommai**: Thanks to [OnommAI](https://onomaai.com/) for open-sourcing a powerful base model. |
| 161 | |
| 162 | - **V-Prediction**: Thanks to the following individuals for their detailed instructions and experiments. |
| 163 | |
| 164 | - adsfssdf |
| 165 | - [bluvoll](https://civitai.com/user/bluvoll) |
| 166 | - [bvhari](https://github.com/bvhari) |
| 167 | - [catboxanon](https://github.com/catboxanon) |
| 168 | - [parsee-mizuhashi](https://huggingface.co/parsee-mizuhashi) |
| 169 | - [very-aesthetic](https://github.com/very-aesthetic) |
| 170 | - [momoura](https://civitai.com/user/momoura) |
| 171 | - madmanfourohfour |
| 172 | |
| 173 | - **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) |