<h3 id="heading-316"><em>我的Pixiv个人主页 / My Pixiv personal homepage: </em><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/17321274"><em>https://www.pixiv.net/users/17321274</em></a></h3><p></p><h3 id="heading-133">这是一个来自Pixiv作者Akiryo（现已停更）的角色搭配——不知火舞。本Lora训练图集不包含任何真人图片。底模使用<a target="_blank" rel="ugc" href="https://civarchive.com/models/10415/3-guofeng3">国风V3.3</a>。参考Lora权重0.75。和国风3.3兼容性较好的模型有：<a target="_blank" rel="ugc" href="https://civarchive.com/models/7371?modelVersionId=46846"><strong>ReV Animated</strong></a><strong>, </strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/4384?modelVersionId=128713"><strong>DreamShaper</strong></a><strong>, </strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/86228"><strong>GCM-Game Concept Map</strong></a><strong>等，你可以尝试使用这些模型进行AI绘图。</strong></h3><h3 id="heading-134"></h3><h3 id="heading-135">This is a character from Pixiv author Akiryo (now discontinued)——Mai Shiranui. This Lora training atlas does not contain any images of real people. The basic mold uses <a target="_blank" rel="ugc" href="https://civarchive.com/models/10415/3-guofeng3"><strong>GuoFeng</strong>V3.3</a>.Reference Lora weight 0.75.Models with good compatibility with Gufeng 3.3 include: <a target="_blank" rel="ugc" href="https://civarchive.com/models/7371?modelVersionId=46846"><strong>ReV Animated</strong></a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/4384?modelVersionId=128713"><strong>DreamShaper</strong></a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/86228"><strong>GCM-Game Concept Map</strong></a>, etc. You can try to use these models for AI drawing.</h3><p></p><h3 id="heading-53">Lora召唤词 / <span style="color:rgb(193, 194, 197)">trigger words</span>：akiryoMAI</h3><h3 id="heading-53"><br />参考正面tag如下——Reference <span style="color:rgb(193, 194, 197)">Prompt</span>：</h3><ul><li><p>akiryoMAI, 1girl, breasts, solo, brown hair, ponytail, lingerie, navel, long hair, bra, brown eyes, black thighhighs, garter belt, looking at viewer,revealing clothes, highleg panties,shiranui mai, high ponytail,choker, cityscape, night, mature female, standing, hand on hip, </p></li></ul><h3 id="heading-139">参考负面tag如下——Reference <span style="color:rgb(193, 194, 197)">Negative prompt</span>：</h3><ul><li><p>(worst quality, low quality:1.4), monochrome, zombie,undefinedEasyNegative, lowres, bad anatomy, bad hands, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,too many fingers, thick lips, oversized head,facing away,extra arms,extra ponytail,bad eyes,fused eyes,distorted eyes,multicolored eyes,small breasts,loli,distorted background, overexposure,</p></li></ul><p></p><h3 id="heading-65">为了更好地展现人物服装特征，我的模型展示图往往使用半身照。事实上，对于绝大多数角色，我都是使用全身素材进行训练。如果你喜欢全身照，请删去cowboy shot后添加full body并尝试添加这些词汇以展示人物的鞋子:high heels 或 boots 或 sandal 或 shoes等。</h3><p></p><h3 id="heading-66">In order to better show the character's clothing characteristics, my model display images often use cowboy shot. In fact, for the vast majority of roles, I train using full-body footage. If you prefer full-body photos, try adding these words after adding full body to show the person's shoes :high heels or boots or sandal or shoes.</h3><p></p><h3 id="heading-142">版权说明：我的Lora训练均使用网络公开图片进行训练，训练后的Lora成品不推荐用于商业用途。如果你用于商业用途，一切风险由你自己承担，我不承担任何责任！</h3><h3 id="heading-143"></h3><h3 id="heading-144">Copyright Note: My Lora training is trained using public images on the Internet, and the Lora is not recommended for commercial use. If you use for commercial purposes, all the risk is borne by you, I do not assume any responsibility!</h3><h3 id="heading-238"></h3><h3 id="heading-239">如果你有喜欢的人物角色，希望将他们做成Lora，你可以联系我帮助你训练Lora模型，不收取任何费用。</h3><h3 id="heading-240"></h3><h3 id="heading-241">If you have a favorite character that you would like to make Lora, you can contact me to help you train Lora models at no charge.</h3><p></p><h3 id="heading-334">我的个人AI交流群：828795031</h3><h3 id="heading-335">入群密码：S82KFCV50</h3><h3 id="heading-336">群内不搞黄，不收费，不教萌新（萌新请自学），欢迎进来交流技术。</h3>

不知火舞（Akiryo版本）_Mai Shiranui（The Akiryo version）

akiryo火舞4005.safetensors

v1.0

Shiranui Dance (Akiryo version) _Mai Shiranui (The Akiryo v

<p>This is a character mix from Pixiv author Akiryo (now discontinued) — Dance Shiranui. This Lora training album does not include any real images. The bottom model uses Guofeng V3.3. Refer to Lora weight 0.75. Models that are more compatible with Guofeng 3.3 include: <strong>Rev</strong> Animated, DreamShaper, GCM-Game Concept Map, etc. You can try using these models</p> for AI drawing. <p>This is a character from Pixiv author Akiryo (now dismissed) ——Mai Shiranui. This Lora training atlas does not contain any images of real people. <strong>The basic mold uses <strong>GuoFeng</strong> V3.3.Reference Lora weight 0.75.Models with good compatibility with Gufeng 3.3 include: ReV Animated, DreamShaper</strong> <strong> </strong>, <strong>GCM-Game Concept Map</strong>, etc. You can try to use these models for AI drawing</p>. <p></p><br><p>Lora's summoning/trigger words: akiryomai <p>reference front tag is as follows - reference prompt:</p> akiryomai</p> <ul><li>, 1girl, breasts, solo, brown hair, ponytail, lingerie, navel, long hair, bra, brown eyes, black thighhighs, garter belt, looking at viewer, revealing clothes, highleg panties, shiranui mai, high ponytail, choker, cityscape, night, mature female, standing, hand on hip,</li> </ul><p>Reference negative tags are as follows - reference negative prompt:</p> <ul><li>(worst quality, low quality: 1.4), monochrome, zombie, undefinedEasyNegative, lowres, bad anatomy, bad hands, text, error, extra digit, Too many fingers, thick lips, oversized head, facing away, extra arms, jpeg artifacts, signature, watermark, username, normal quality, jpeg artifacts, signature, watermark, username, blurry </li></ul><br><p>extra ponytail, bad eyes, fused eyes, distorted eyes, multicolored eyes, small breasts, loli, distorted background, overexposure. In order to better show the character's clothing characteristics, I often use a bust shot on my model.<p></p> In fact, for the vast majority of characters, I use full-body material for training. If you like full body shots, delete the cowboy shot and add full body and try adding these words to show the character's shoes: high heels or boots or sandals or shoes, etc</p>. <p></p><br><p>In order to better show the character's clothing accessories, my model display images often use cowboy shots. In fact, for the vast majority of roles, I Train using full-body footage. If you prefer full-body photos, try adding these words after adding full body to show the person's shoes: high heels or boots or sandals or shoes.</p> <p></p><br><p>Copyright statement: My Lora training uses public images on the Internet for training, and finished Lora products after training are not recommended for commercial use. If you use it for commercial purposes, you do so at your own risk, and I'm not responsible for anything!</p> <p>Copyright Note: My Lora training is using public images on the Internet, and the Lora is not recommended for commercial use. If you use for commercial reasons, all the risks are borne by you, I do not assume any responsibility!</p> <p>If you have characters you like and want to make them Lora, you can contact me to help you train the Lora model at no cost.</p> <p>If you have a favorite character that you would like to make Lora, you can contact me to help you train Lora models at no charge.</p> <p></p><br><p>My personal AI exchange group: 828795031 Join the group password:</p> <p>S82KFCV50 There is no yellow in the group</p>, no fees, and no teaching of Mengxin (Mengxin, please learn by yourself). Welcome to exchange <p>technology</p>.

Files with SHA256: 93a375936f04536986e681042dbd59fab9c69f72d43c0ba977f96f65040eac17