masterpiece, best quality, outdoors,  closed eyes, smile, <lora:Yumemi_v2:1>
masterpiece, best quality, <lora:Yumemi_v2:0.95>
masterpiece, best quality, outdoors, looking at viewer, from below,  <lora:Yumemi_v2:1>
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

V2.0

2.0的泛化有稍微降低,推荐权重1,此次更新主要是fullbody的特化,对下半身服装做了一定优化,所以对Tag:fullbody极为敏感,谨慎使用。使用2.0建议加入视角类,姿势类Tag,否则您可能会得到单一姿势的生成图,咱一直在追求服饰配饰的还原度,但进度缓慢,只能慢慢来。顺便,2.0直出图可能质量普遍有所降低,所以想要高质量出图更依赖于高清修复,Tag尽量详细,这都是出高质量图的必要条件。

2.0 generalization has slightly reduced, recommended weight 1, this update is mainly fullbody specialization, the lower body clothing to do some optimization, so extremely sensitive to Tag: fullbody, use with caution. Using 2.0 is recommended to add perspective class, pose class Tag, otherwise you may get a single pose generation chart, we have been in pursuit of the degree of restoration of clothing and accessories, but the progress is slow, only slowly!By the way, the quality of 2.0 straight images may generally decrease, so high-quality images rely more on high-definition repair, and tags should be as detailed as possible. These are all necessary conditions for producing high-quality images.

2.0の汎化はやや低下しており、重み1を推奨しているが、今回のアップデートは主にフルボディに特化しており、下半身の服装に一定の最適化をしているため、Tag:フルボディに極めて敏感で、慎重に使用している。2.0を使って画角類、姿勢類Tagを加えることを提案します。そうしないと、単一の姿勢の生成図が得られる可能性があります。私たちはずっと服飾アクセサリーの還元度を求めていますが、進度は遅く、ゆっくりしかできません。ちなみに、2.0直出図は一般的に品質が低下している可能性があるので、高品質出図をよりハイビジョン修復に依存したい場合は、Tagをできるだけ詳細にすることが高品質図を出すための必要条件です。

V1.0

推荐权重0.6左右,请根据不同Checkpoint模型进行不同的权重调整,以达到最佳效果
测试Anything4.5,DOSMIX,PVCStyleModel,CounterfeitV25等Checkpoints模型的兼容性都不错
缺点:背景容易异常,发光缎带容易异常,以后可能会进行优化

请勿使用本模型生成的图片发往Pixiv!

请勿使用本模型生成R18发往公众平台!

若发现违规,本人将会删除此模型。

The recommended weight is around 0.6. Please adjust the weight according to different Checkpoint models to achieve the best results

Testing the compatibility of Checkpoints models such as Anything4.5, DOSMIX, PVCStyleModel, and CounterfeitV25 is good

Disadvantages: The background is prone to abnormalities, and the luminous ribbon is prone to abnormalities, which may be optimized in the future

Do not use the images generated by this model to send to Pixiv!

Do not use this model to generate R18 and send it to the public platform!

If any violations are found, I will delete this model.

推奨ウェイト0.6前後、Checkpointモデルによって異なるウェイト調整を行い、最適な効果を達成してください

Anything 4.5、DOSMIX、PVC StyleModel、CounterfeitV 25などのCheckpointsモデルの互換性をテストするのに良い

欠点:背景が異常になりやすく、発光リボンが異常になりやすく、後で最適化される可能性がある

このモデルで生成された画像をPixivに送信しないでください!

本モデルを使用してR 18を生成して公衆プラットフォームに送信しないでください!

違反が検出されると、このモデルは削除されます。

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.