圖片來源: Image-to-Image Translation with Conditional Adversarial Networks官網
透過特定的圖像資料集來訓練,製作一個自動依據邊緣形狀形成特定內容的圖像生成AI。
應用面:
The paper regarding on this investigation was written in 2016 by four scholars at UC Berkeley where it looks at the use of conditional adversarial network as the solution to image-to-image translation problems. Before going into the application of pix2pix, I want go over a little about what “conditional adversarial nets” is.
Conference: 2017 IEEE Conference on Computer Vision and Pattern Recognition CVPR
By the end of this article, you will have a comprehensive understanding of image-to-image translation with conditional adversarial networks and how to apply it in practice.
This article aims to explain the key ideas behind conditional adversarial networks and provide insights into their implementation and training process.
Image-to-image translation is the controlled conversion of a given source image to a target image. Examples include translating a photograph of a landscape from day to night or translating a segmented image to a photograph, synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
The Pix2Pix Generative Adversarial Network, or GAN, is an approach to training a deep convolutional neural network for image-to-image translation tasks.
圖片來源: Civitai官網
Civitai是一個提供AI藝術資源分享和發現的平台,主要幫助用戶輕鬆探索並使用各類AI藝術模型。平台用戶可以上傳和分享自己用AI生成的圖像,也可瀏覽或下載其他用戶創建的圖像。這些圖像可以與AI藝術軟件一起使用,生成個性化、獨特的藝術作品。
點擊人數: 77331 +
圖片來源: Draw Together with a Neural Network官網
Magenta是由Google Brain創建的一個開源項目,其中SketchRNN圖像生成工具的Draw Together with a Neural Network頁面可以讓人可以和AI共創塗鴉。
點擊人數: 2755 +
圖片來源: Let’s Enhance官網
Let’s Enhance可使放大圖片後產生的模糊、失真情形,或是JPEG產生的雜訊問題,都能得到改善,也會調整相片的對比和亮度品質,提升相片呈現的品質,並且新增了輸入文字生成圖像的功能,讓創作更加多元快速。
點擊人數: 10010 +
工具分類建議
感謝您的建議,我們將廣搜意見後優化分類!