此嵌入專注於修正手指數量與形狀問題，可能導致模型風格改變<ul><li>v5:<ul><li>negative_hand-neg訓練於10張圖像而成。</li></ul></li><li>v22<ul><li>使用75個vector，訓練資料使用v5與其他負面嵌入產生的兩百張圖像。</li></ul></li><li>v49<ul><li>使用32個vector，訓練資料使用不同風格模型與其他負面嵌入產生的六百張圖像。</li></ul></li></ul>Translated by ChatGPTThis embedding focuses on correcting issues related to the number and shape of fingers, which may result in a change in the model's style.<ul><li>v5:<ul><li>negative_hand-neg is trained on 10 images.</li></ul></li><li>v22:<ul><li>Utilizing 75 vectors, the training data consists of 200 images generated from v5 and other negative embeddings.</li></ul></li><li>v49<ul><li>Utilizing 32 vectors, the training data consists of 600 images generated from different style models and other negative embeddings.</li></ul></li></ul><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/teddy92729">https://www.buymeacoffee.com/teddy92729</a><a target="_blank" rel="ugc" href="https://ko-fi.com/teddy92729">https://ko-fi.com/teddy92729</a>

myself-badhand

The training data is generated from the old version and other negative embeddings, totaling 600 images with dimensions of 512*512.32 vectors per token.

Files with SHA256: 764c2f93aaf5e570e03280c8605373b1f2c4e18bb6e2506e579f11128e6bba61