Tensor.Art
Create

Nobi Nobita WAI-IL7γ（野比のび太 from 『ドラえもん』）

LORA
Original

Updated:

WLγ V1

For WAI illustrious V7.

WAI illustrious V7での使用を想定したLoraです。

https://tensor.art/models/796852047271109746

The training settings are almost the same as WLβ, but the dataset is different. This version is more stable than WLβ in terms of drawing standing characters, but it is almost impossible to achieve complex compositions.

トレーニング設定はWLβとほぼ同じですが、データセットが異なります。立ち絵の描画に関してはWLβよりも安定していますが、複雑な構図を実現するのはほぼ不可能です。

Version Detail

Illustrious
Compared to the WLα, the prompt followability has been improved, but it is still a bit of a fussy model. Sometimes Nobita's glasses come off. When the glasses fall off, adding the “glasses” prompt usually does the trick. However, if you usually add the “glasses” prompt, you will now get a different pair of glasses than Nobita's. The “glasses” is an insurance in case the glasses come off. WLαに比べてプロンプト追従性も向上しましたが、それでもまだちょっと気難しいモデルです。ときどきのび太君の眼鏡が外れたりします。眼鏡が外れたら、「glasses」プロンプトを追加するとたいていうまくいきます。しかし、「glasses」プロンプトを普段入れてしまうと、今度はのび太くんのとは違う眼鏡が出てきます。「glasses」は眼鏡が外れたとき用の保険です。 If it does not draw well with txt2img one time, it works rather well with img2img if you draw over it with the same prompt. txt2imgの一回でうまく描画されない場合は、img2imgで同じプロンプトのまま上書きするとわりとうまくいきます。

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.