Our website is made possible by displaying online advertisements to our visitors.
Please consider supporting us by disabling your ad blocker.

Responsive image


Stable Diffusion

Stable Diffusion動態標誌
向Stable Diffusion落指令,叫佢畫個太空人騎馬

Stable Diffusion係個可以將文字轉化做圖像嘅深度學習人工智能模型,基於擴散模型嘅,2022年推出。訓練數據係嚟自 LAION-5B 嘅圖像同對應嘅描述文字。LAION-5B 係德國非牟利組織 LAION 所整嘅,基於 Common Crawl 數據,當中50億對圖文組合以語言、含有水印嘅機率、解像度等分成幾個數據集。


Previous Page Next Page