<h2 id="https:discord.ggtajbr2dqdy-is-the-link-to-discord-there-are-two-channels-chinese-and-english-e40dvbkhi"><a target="_blank" rel="ugc" href="https://discord.gg/TajBR2Dqdy">https://discord.gg/TajBR2Dqdy</a> is the link to discord, there are two channels, Chinese and English</h2><h3 id="qq451450868-k440oh5v2">QQ群：451450868（主群）</h3><h3 id="929721518-4kekh1xn3">929721518备用群</h3><p>v7 tensor onsite use link<a target="_blank" rel="ugc" href="https://tensor.art/models/828862176283372046/T-illunai3-v7">T-illunai3 - v7 | Stable Diffusion Model - Checkpoint | </a><a target="_blank" rel="ugc" href="http://Tensor.Art">Tensor.Art</a></p><p>v7国内线上出图平台<a target="_blank" rel="ugc" href="https://tusiart.com/models/828862176283372046">T-illunai3 - v7 | Stable Diffusion Model - Checkpoint | </a><a target="_blank" rel="ugc" href="http://Tensor.Art">Tensor.Art</a><a target="_blank" rel="ugc" href="https://tusiart.com/models/828862176283372046"> (</a><a target="_blank" rel="ugc" href="http://tusiart.com">tusiart.com</a>)</p><p></p><h2 id="this-is-a-donation-channel-thank-you-very-much-for-your-support-all-the-funds-will-be-used-to-purchase-5090dbuy-tonade-a-coffee.-ko-fi.comtonade-ko-fi-where-creators-get-support-from-fans-through-donations-memberships-shop-sales-and-more!-the-original-'buy-me-a-coffee'-page.-ak7py5k7g">This is a donation channel Thank you very much for your support！ All the funds will be used to purchase 5090d！<a target="_blank" rel="ugc" href="https://ko-fi.com/tonade">Buy Tonade a Coffee. </a><a target="_blank" rel="ugc" href="http://ko-fi.com/tonade">ko-fi.com/tonade</a><a target="_blank" rel="ugc" href="https://ko-fi.com/tonade"> - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.</a></h2><h2 id="tonadet-ponynai3cidtonadet-illunai3-or-(ifdian.net)-y7wmtxsq3"><a target="_blank" rel="ugc" href="https://ifdian.net/a/Tonade">Tonade正在创作T-ponynai3模型作者，c站id：Tonade，现在是T-illunai3作者 | 爱发电 (</a><a target="_blank" rel="ugc" href="http://ifdian.net">ifdian.net</a><a target="_blank" rel="ugc" href="https://ifdian.net/a/Tonade">)</a> 这是国内爱发电的链接，感谢捐赠支持！</h2><h2 id="-wkxjdrngw"></h2><h1 id="noob-1.0-1000-(qq.com)-4cyf1b6n2"><a target="_blank" rel="ugc" href="https://docs.qq.com/sheet/DZFRkR2p4aWx5TkZL?tab=9v7zie&amp;_t=1739375964829&amp;nlc=1&amp;u=abc7f793042a45c5a4bc179dc1026ae1">NOOB 1.0版本 1000 单画师测试不可修改版 (</a><a target="_blank" rel="ugc" href="http://qq.com">qq.com</a><a target="_blank" rel="ugc" href="https://docs.qq.com/sheet/DZFRkR2p4aWx5TkZL?tab=9v7zie&amp;_t=1739375964829&amp;nlc=1&amp;u=abc7f793042a45c5a4bc179dc1026ae1">)</a></h1><h1 id="illuillunai-v7-q09h0gboe"><span style="color:rgb(64, 192, 87)">可直接对照参考的画师提示词文档，可在illu系模型上完美使用，包括illunai-v7</span></h1><h1 id="noob-1.0-1000-(qq.com)it-can-be-directly-compared-with-the-reference-artist's-prompt-word-document-and-can-be-perfectly-used-on-illu-models-including-illunai-v7-7cm9ikcp8"><a target="_blank" rel="ugc" href="https://docs.qq.com/sheet/DZFRkR2p4aWx5TkZL?tab=9v7zie&amp;_t=1739375964829&amp;nlc=1&amp;u=abc7f793042a45c5a4bc179dc1026ae1">NOOB 1.0版本 1000 单画师测试不可修改版 (</a><a target="_blank" rel="ugc" href="http://qq.com">qq.com</a><a target="_blank" rel="ugc" href="https://docs.qq.com/sheet/DZFRkR2p4aWx5TkZL?tab=9v7zie&amp;_t=1739375964829&amp;nlc=1&amp;u=abc7f793042a45c5a4bc179dc1026ae1">)</a><span style="color:rgb(64, 192, 87)">It can be directly compared with the reference artist's prompt word document and can be perfectly used on Illu models, including illunai-v7</span></h1><h3 id="-an58t6dvy"></h3><p></p><h1 id="v6-wmasmjoog"><span style="color:rgb(253, 126, 20)">v6推荐使用的提示词（</span>懒人版）</h1><h1 id="recommended-prompt-words-for-v6lazy-version-mt3d86791"><span style="color:rgb(253, 126, 20)">Recommended prompt words for v6（</span>Lazy version<span style="color:rgb(253, 126, 20)">）</span></h1><h3 id="positivebest-qualityamazing-qualityvery-o99ro1w4p"><span style="color:rgb(253, 126, 20)">POSITIVE：</span>best quality,amazing quality,very</h3><h3 id="aestheticabsurdresmasterpiece-qkd2vsdyj">aesthetic,absurdres,masterpiece,</h3><h3 id="negativebad-feetmissing-toesextra-toeslowresbad-anatomybad-handstexterrormissing-fingersextra-digitfewer-digitscroppedworst-qualitylow-qualitynormal-qualityjpeg-artifactssignaturewatermarkusernameblurry4-komasketch(bad:1.05)errorfewerextramissingworst-qualityjpeg-artifactsbad-qualitywatermarkunfinisheddispleasingchromatic-aberrationsignatureextra-digitsartistic-errorusernamescanabstract(blurry-lowres-low-quality:1.1)ugly(big-head-bad-anatomy:1.05)artist-name(watermark:1.1)-eaavntdaw"><span style="color:rgb(253, 126, 20)">NEGATIVE：</span>bad feet,missing toes,extra toes,lowres,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,4-koma,sketch,(bad:1.05),error,fewer,extra,missing,worst quality,jpeg artifacts,bad quality,watermark,unfinished,displeasing,chromatic aberration,signature,extra digits,artistic error,username,scan,abstract,(blurry, lowres, low quality:1.1),ugly,(big head, bad anatomy:1.05),artist name,(watermark:1.1),</h3><p></p><h1 id="v1pony-acstn9u13">v1只是一个初步进行微调的版本，但是效果好的惊人。在动漫绘画的领域比pony的微调效果要好上不少，肢体的正确率也十分可观。希望各位能多多测试一下这个微调。</h1><h1 id="illustrious-xl-illustrious-xl-v0.1-or-stable-diffusion-xl-checkpoint-or-civitai-c2z0b1md6"><span style="color:rgb(253, 126, 20)">基于illustrious-xl </span><a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint | Civitai</a></h1><h1 id="v1-just-a-preliminary-version-with-fine-tuning-but-the-results-are-surprisingly-good.-in-the-field-of-anime-painting-the-fine-tuning-effect-is-much-better-than-pony's-and-the-accuracy-of-body-movements-is-also-considerable.-i-hope-everyone-can-test-this-fine-tuning-and-give-some-comments-about-it.-z6hz16yaw">V1 just a preliminary version with fine-tuning, but the results are surprisingly good. In the field of anime painting, the fine-tuning effect is much better than Pony's, and the accuracy of body movements is also considerable. I hope everyone can test this fine-tuning and give some comments about it.</h1><h1 id="base-on-illustrious-xl-illustrious-xl-v0.1-or-stable-diffusion-xl-checkpoint-or-civitai-17y7yuigr"><span style="color:rgb(253, 126, 20)">base on illustrious-xl </span><a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL - v0.1 | Stable Diffusion XL Checkpoint | Civitai</a></h1><p></p><h3 id="-asi3fmg3x"><span style="color:rgb(190, 75, 219)">训练须知：</span></h3><h3 id="v1100nai3prodigyillustrious-bftylq6mk">v1版本使用了100张经过筛选的高质量的使用nai3生成的图片，以及画风相近的一些公开素材作为姿势的补充，训练使用了prodigy算法进行训练。illustrious模型的女性素材很多，导致了模型会比较难以生成男性的图像，而且某些时候需要一些比较复杂的提示词才能生成目标图像，这将在之后的更多训练集的版本尝试进行一些改善。</h3><h3 id="training-instructions:-9mwud0e3k"><span style="color:rgb(190, 75, 219)">Training instructions:</span></h3><h3 id="the-v1-version-used-100-high-quality-images-generated-using-nai3-that-had-been-filtered-as-well-as-some-publicly-available-materials-with-similar-art-styles-as-pose-supplements.-the-training-was-conducted-using-the-&quot;prodigy&quot;-to-train.-the-illustrious-model-has-a-lot-of-female-materials-which-makes-it-difficult-for-the-model-to-generate-male-images-and-sometimes-requires-some-complex-prompt-words-to-generate-target-images.-this-will-be-improved-in-more-training-set-versions-in-the-future.-9zlwwxuuc">The v1 version used 100 high-quality images generated using Nai3 that had been filtered, as well as some publicly available materials with similar art styles as pose supplements. The training was conducted using the "prodigy" to train. The illustrious model has a lot of female materials, which makes it difficult for the model to generate male images, and sometimes requires some complex prompt words to generate target images. This will be improved in more training set versions in the future.</h3><h3 id="-qfynuzjnv"></h3><h3 id="v4600nai3illustriousfine-tuningnoobilluprompt-d6bpv5frx">在v4中，我使用了600张由nai3生成的风格图片作为默认画风的训练，这一步是基于illustrious模型的，然后我用模型融合的方法在这一fine-tuning后的模型上加入了一些noob的模型成分，以来平衡illu的一些缺失的语义和识别prompt的能力。</h3><h3 id="in-v4-i-used-600-style-images-generated-by-nai3-as-the-default-art-style-for-training.-this-step-was-based-on-the-illustrious-model-and-then-i-added-some-noob-model-components-to-this-fine-tuned-model-using-model-fusion-to-balance-some-of-illu's-missing-semantics-and-prompt-recognition-ability.-3vx2pvbu9">In v4, I used 600 style images generated by nai3 as the default art style for training. This step was based on the illustrious model, and then I added some noob model components to this fine tuned model using model fusion to balance some of Illu's missing semantics and prompt recognition ability.</h3><p></p><h2 id="v6ntrv4nai3nai3-06xme31vu">v6这个版本的模型进行了更好的画风调教，改善了大量的基于ntrv4的错误肢体和过拟合的画风，并调整了过细的线条，让整体的线条和效果更好，甚至配合画师提示词使用已经足以媲美nai3，在某些画面构图上已经超越了nai3</h2><h2 id="ntr-nsnpjjabd">推荐使用的提示词都在例图里面，总体来说ntr模型系列的提示词都可以直接使用，这将是一个新的开始，往后会不断强化这个版本</h2><h2 id="this-version-v6-of-the-model-has-undergone-better-art-style-tuning-improving-a-large-number-of-erroneous-limbs-and-overfitting-styles-based-on-ntrv4-and-adjusting-overly-fine-lines-to-make-the-overall-lines-and-effects-better.-even-when-used-in-conjunction-with-artist-prompts-it-is-already-comparable-to-nai3-and-has-surpassed-nai3-in-some-picture-compositions-cl8nwj9xy">This version v6 of the model has undergone better art style tuning, improving a large number of erroneous limbs and overfitting styles based on ntrv4, and adjusting overly fine lines to make the overall lines and effects better. Even when used in conjunction with artist prompts, it is already comparable to nai3 and has surpassed nai3 in some picture compositions、</h2><h2 id="the-recommended-prompt-words-are-all-in-the-example-image.-overall-the-prompt-words-of-the-ntr-model-series-can-be-directly-used-which-will-be-a-new-beginning-and-will-be-continuously-strengthened-in-the-future-p55cj755f">The recommended prompt words are all in the example image. Overall, the prompt words of the ntr model series can be directly used, which will be a new beginning and will be continuously strengthened in the future</h2><h3 id="-fd7mjt19e"></h3><h2 id="recommend-quality-words-q452pkz2x">推荐使用质量词Recommend quality words</h2><p><strong><span style="color:rgb(76, 110, 245)">正面提示词</span></strong></p><p>best quality,amazing quality,very aesthetic,absurdres,beast quality,masterpiece,artist:xxx</p><p><strong><span style="color:rgb(76, 110, 245)">负面提示词</span></strong></p><p>lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,4-koma, sketch, (bad:1.05), error, fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, (blurry, lowres, low quality:1.1), ugly, (big head, bad anatomy:1.05), artist name, (watermark:1.1)</p><p></p><h2 id="recommend-using-quality-words-1ly6vqb4d">Recommend using quality words</h2><p><strong><span style="color:rgb(76, 110, 245)">Positive prompt words</span></strong></p><p>best quality,amazing quality,very aesthetic,absurdres,masterpiece,artist:xxx</p><p><strong><span style="color:rgb(76, 110, 245)">Negative prompt words</span></strong></p><p>lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,4-koma, sketch, (bad:1.05), error, fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, (blurry, lowres, low quality:1.1), ugly, (big head, bad anatomy:1.05), artist name, (watermark:1.1)</p><p></p><p><strong>在线生成网址 online generation link:</strong> <a target="_blank" rel="ugc" href="https://tusiart.com/models/807769140921125111">(340) T-illunai3 - v4 | Stable Diffusion Model - Checkpoint | </a><a target="_blank" rel="ugc" href="http://Tensor.Art">Tensor.Art</a><a target="_blank" rel="ugc" href="https://tusiart.com/models/807769140921125111"> (</a><a target="_blank" rel="ugc" href="http://tusiart.com">tusiart.com</a>)</p><p>ps: For some unknown reasons, my model cannot run online on Civitai, even after multiple applications, it is useless. Therefore, I uploaded it to this platform synchronously, and online generation of the model can also be done on it</p><p>出于一些未知的原因，我的模型无法在civitai上在线运行，即使多次申请都无济于事，所以我同步上传了这个平台，在上面同样可以进行该模型的在线生成</p>

T-noobnai3

<p>这个版本是基于noobai的early access版本进行训练的一个版本，使用了多样的经过筛选的522图进行额外画风以及脚部的训练，强化了部分noobai的画风问题，以及一部分画面过于扁平的问题，并且相较于v1，nai3的画风效果没有那么固化，因为训练集足够大能让我放进更多适合中和画风的内容，这个版本训练了200个epoch，在3090显卡上训练了36个小时</p><p>This version is based on the early access version of NOOBAI for training, using a variety of filtered 522 images for additional art style and foot training, strengthening some of NOOBAI's art style issues and some of the flat images. Compared to v1, the art style effect of Nai3 is not as rigid because the training set is large enough for me to include more content suitable for neutral art styles. This version was trained for 200 epochs and 36 hours on a 3090 graphics card</p>

Files with SHA256: 521c1638d9f880f16264e531b40cd4323134b358749b1eb161fca4e8dfff592b