TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

How to Train an AI Image Model on Yourself

207 点作者 aberoham4 个月前

10 条评论

ramoz4 个月前
FYI: For Flux, there is a lot more power in the text-encoder &amp; you can prompt with more meaningful and comprehensive sentences. Thus, less of the traditional comma separated &amp; concise phrasing we saw in stable diffusion.<p>You should do the same with your training images. Caption everything you do not want the model to remember as &quot;you&quot; (what you&#x27;re doing, wearing, accompanied by, accessories, etc).
评论 #42906824 未加载
评论 #42890088 未加载
isoprophlex4 个月前
I did this for our beloved, dead cat... On replicate, too. I loved the results, until at one point I suddenly got really creeped out about the thing I was doing.
评论 #42889916 未加载
petercooper4 个月前
Replicate does make this particularly easy while still being somewhat developer focused. I&#x27;ve used it for a few people in our group chat so we can make silly in-joke memes and stuff and the results are quite stunning. Replicate then offers the model up over a simple API (shown in the post) if you wanted to let people generate right from the chat, etc. Replicate is worth poking around a bit more broadly, too, they have some interesting models on there (though the pricing tends not to be very competitive if you were going to do it at scale.)
manishsharan4 个月前
This is fantastic but now you need to train a model to detect AI generated images from actual photos. Then of course , a model to beat the detector model and then a model to catch the model that beats the detector model and so on.<p>Thank you from people holding NVDA.
评论 #42890155 未加载
thefourthchime4 个月前
I did this a while back, though it was pictures of my wife in lingerie.<p>- I asked grok to generate a list of racey prompts. - Has replicate generate them via script. About 10-20% are very poor, I filtered those out manually. - It also has NSFW guardrails, but a simple retry or word juggle gives you a chance to get around it.<p>I think I spent $10
评论 #42891257 未加载
ge964 个月前
What I want is to be able to feed in a bunch of videos and generate an animatable (from talking) 3D face from that data. I suppose you in theory only need 3 images (front and sides). But mapping pixels to motion is interesting (facial expressions).<p>There wouldn&#x27;t be depth data so it would be inferred from shadows
评论 #42890226 未加载
评论 #42890584 未加载
deadbabe4 个月前
I’m imagining something where an influencer trains AI to make and post images of themselves on social media, then the influencer dies but the AI keeps going forever.
评论 #42891184 未加载
m4634 个月前
I had set up automatic1111 a while back, and I believe the webui let you your image generation have a starting image. It&#x27;s kind of fun to have a cartoon of yourself based on an image.
njx4 个月前
Thank you for sharing. Is there any model that can help train convert pictures into cartoon or flat vector illustration?
评论 #42891938 未加载
DoodahMan4 个月前
is something like this possible to do with video yet?
评论 #42894151 未加载
评论 #42906830 未加载