<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
<span style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">Hi Daniel,</span><br style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">
<span style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">We’re hoping to include it in 8.8.0 (this fall). I’ve been working on it for about a month now.</span><br style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">
<br style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">
<span style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-size: 14.666667px;">Here’s a sample:</span>
<div><font color="#000000"><span style="caret-color: rgb(0, 0, 0); font-size: 14.666667px;"><br id="lineBreakAtBeginningOfMessage">
</span></font>
<div><img src="cid:D3A48705-E76C-4D72-B07F-E1B077866B93" alt="Screenshot 2025-05-12 at 6.57.09 PM.png" width="320"></div>
<div><br>
</div>
<div>Cheers,</div>
<div>Mike</div>
<div><br>
</div>
<div><br>
<blockquote type="cite">
<div>On May 31, 2025, at 12:05 PM, Daniel Bauer <linux@daniel-bauer.com> wrote:</div>
<br class="Apple-interchange-newline">
<div>
<div>In March I asked for curiosity about AI features to generally recognize image content. I understand that on one hand "open source" is important, and on the other hand, consumer PC's lack enough power.<br>
<br>
You probably know it, but just in case if not:<br>
https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhuggingface.co%2Fspaces%2Ffancyfeast%2Fjoy-caption-beta-one&data=05%7C02%7C%7Cb684383f063e4d6e215208dda05cfd14%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C638843043425729047%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=kgZ0DEDuFgvDXdHCkgIT7T%2BzrebqniG%2BieKbqP59PoA%3D&reserved=0<br>
does a fantastic job in describing image content (even NSFW).<br>
<br>
But my local install of course is too slow to be useful for mass captioning, even using CUDA.<br>
<br>
But as it is open source I thought, looking into it could feed you with ideas, maybe for a lightweight version...<br>
<br>
:-)<br>
<br>
Have a nice weekend<br>
<br>
Daniel<br>
-- <br>
Daniel Bauer photographer Basel Málaga<br>
Twitter: @Marsfotografo (often explicit nudes)<br>
https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.patreon.com%2Fdanielbauer&data=05%7C02%7C%7Cb684383f063e4d6e215208dda05cfd14%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C638843043425746484%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=R6K2M0GQPdeIZF1NaRhrqXou0WYZwm5VPiipBQEecrk%3D&reserved=0<br>
https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.daniel-bauer.com%2F&data=05%7C02%7C%7Cb684383f063e4d6e215208dda05cfd14%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C638843043425756693%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=3VvtZieAXuAZN8kJpRBODuLB0fcCGtZ8pKOd7asVWJY%3D&reserved=0
(nudes)<br>
<br>
</div>
</div>
</blockquote>
</div>
<br>
</div>
</body>
</html>