<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Valentine about AI - Medium]]></title>
        <description><![CDATA[Making sense of the AI world - Medium]]></description>
        <link>https://medium.com/valentine-ai?source=rss----29c9c9af6366---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Valentine about AI - Medium</title>
            <link>https://medium.com/valentine-ai?source=rss----29c9c9af6366---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 00:31:14 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/valentine-ai" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Overview of Generative AI Services from AWS]]></title>
            <link>https://medium.com/valentine-ai/overview-of-generative-ai-services-from-aws-ebc9b0b5dc36?source=rss----29c9c9af6366---4</link>
            <guid isPermaLink="false">https://medium.com/p/ebc9b0b5dc36</guid>
            <category><![CDATA[amazon-titan]]></category>
            <category><![CDATA[amazon-q]]></category>
            <category><![CDATA[amazon-bedrock]]></category>
            <dc:creator><![CDATA[Valentin Despa]]></dc:creator>
            <pubDate>Mon, 11 Mar 2024 17:15:05 GMT</pubDate>
            <atom:updated>2024-03-15T15:38:22.653Z</atom:updated>
            <content:encoded><![CDATA[<h4>Navigating from the AI services from AWS can feel like going through the jungle. In this article, I will go over the most popular GenAI services from AWS and try to give you an overview</h4><h3>Amazon Bedrock</h3><p>When talking about Amazon Bedrock, quite often the focus is on building applications. However, at its core, Amazon Bedrock is not a platform for building applications. What Amazon Bedrock actually does is to provide access to a wide range of foundational models such as Claude, Llama 2, and Stable Diffusion. You can also fine-tune models to with your data.</p><p>In the end, Amazon Bedrock manages the models you wish to use and you can interact with these models through the API.</p><p><strong>In conclusion, Amazon Bedrock is a back-end service and useful only for people with software development skills.</strong> There is no graphical user interface (GUI) that is being generated by Amazon Bedrock.</p><h3>Amazon Q</h3><p>Amazon Q can refer to two things at the same time: a chatbot that can help you use AWS services and the actual name of a service that you can use on AWS.</p><p>I will be talking about the Amazon Q service which lets you build a “ChatGPT” for your business. In a nutshell, you can use your own internal documents as a source, AWS storage services (such as S3, RDS, and a few others), or connect to 3rd party services (such as Gmail, Microsoft Exchange, Dropbox, Google Drive — the list is long).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*g6rS4vWuem5QvexCTPpOYQ.png" /></figure><p>This is what Amazon Q can look like once it has been configured:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bO481czRL_31mVtK78954Q.png" /></figure><p>In the background, Amazon Q actually builds upon Amazon Bedrock.</p><h3>Amazon SageMaker</h3><p>This is a fully managed service that provides the ability to build, train, and deploy machine learning models (ML models).</p><p>SageMaker goes beyond Gen AI and is a more “traditional” service for working with ML models, not just models focused on generative AI.</p><h3>Conclusion</h3><p>I hope this article helped you better understand which GenAI services AWS offers. Leave a comment in the section below if you have any questions. I would love to hear from you!</p><p><strong>Thank you for sticking with this article until the end. If you enjoyed it, please leave a comment, share, and press that 👏 a few times (up to 50 times). It will help others discover this information, and maybe it will help someone else as well.</strong></p><p><strong>Follow me on Medium and </strong><a href="https://www.youtube.com/channel/UCzAnXB3voQGeW-9Hi8X6vpg"><strong>YouTube</strong></a><strong> if you’re interested in more content like this one.</strong></p><h3>References</h3><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ebc9b0b5dc36" width="1" height="1" alt=""><hr><p><a href="https://medium.com/valentine-ai/overview-of-generative-ai-services-from-aws-ebc9b0b5dc36">Overview of Generative AI Services from AWS</a> was originally published in <a href="https://medium.com/valentine-ai">Valentine about AI</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Create Aitana Lopez with Stable Diffusion XL Running on the AWS Cloud]]></title>
            <link>https://medium.com/valentine-ai/create-aitana-lopez-with-stable-diffusion-xl-running-on-the-aws-cloud-5b7ff92e6765?source=rss----29c9c9af6366---4</link>
            <guid isPermaLink="false">https://medium.com/p/5b7ff92e6765</guid>
            <category><![CDATA[fooocus]]></category>
            <category><![CDATA[aws]]></category>
            <category><![CDATA[gradio]]></category>
            <category><![CDATA[aitana-lopez]]></category>
            <category><![CDATA[sdxl]]></category>
            <dc:creator><![CDATA[Valentin Despa]]></dc:creator>
            <pubDate>Thu, 21 Dec 2023 20:36:58 GMT</pubDate>
            <atom:updated>2023-12-22T08:09:05.386Z</atom:updated>
            <content:encoded><![CDATA[<h4>AI-generated models like Aitana Lopez have been making the headlines recently [1] and have quite a following on Instagram [2]. In this tutorial, we will recreate Aitana using the Stable Diffusion XL model, a UI called Fooocus and we will run everything on the capable AWS infrastructure which is optimized for such use-cases.</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*TMMQxtq2lWwpoa8rB41n5Q.png" /></figure><h3>Why run AI models on AWS?</h3><p>Popular YouTuber Jeff Delaney (Fireship) has already provided a <a href="https://www.youtube.com/watch?v=ky5ZB-mqZKM">blueprint for achieving this</a> [3], but if you don’t have the hardware to run this AI image generation model locally, it is best to jump ship (pun intended) and take your business to the cloud.</p><p>There is no secret that these models will overwhelm your CPU/GPU and that anything you do will be extremely sluggish. Yes, you will save a few bucks but you will likely waste a lot of time trying to get this to run locally.</p><h3>TLDR for AWS experts</h3><p>If you already know what you are doing, here are the exact steps you need to do:</p><ol><li>Start a new instance using a <em>Deep Learning AMI from AWS</em> (example ami-0e2a8e53cc348e22b — <em>Deep Learning OSS Nvidia Driver AMI GPU PyTorch 2.0.1 (Amazon Linux 2) 20231214)</em> and a G4 instance type that has the Nvidia GPU (search for g4nd).</li><li>SSH into the instance and run these commands:</li></ol><pre>git clone https://github.com/lllyasviel/Fooocus.git<br>cd Fooocus<br>python3 -m venv fooocus_env<br>source fooocus_env/bin/activate<br>pip install -r requirements_versions.txt<br>python entry_with_update.py --share</pre><p>3. Configure authentication by creating the auth.json file and changing the default credentials.</p><pre>cp auth-example.json auth.json</pre><p>3. Once the app has been started successfully, open the public URL mentioned in the logs, which is something like <a href="https://abcdef123456789.gradio.live/">https://abcdef123456789.gradio.live</a> and log in.</p><p>4. Use the following prompt to generate an image that resembles Aitana Lopez:</p><pre>Adult female, full body, realistic, 35 years old, Spanish descent, Instagram yoga pose, wearing tank top, yoga pants, barefoot, bright neon pink hair, long, slightly curly, messy style, thin long face, V-shaped face, extremely slender build, small mole on left side of neck, skin imperfections, dark very thin eyebrows, one eyebrow raised, head tilted to the right, suspicious expression, dark brown eyes, medium breasts, no makeup.</pre><p>5. Don’t forget to terminate the AWS instance once you don’t need it anymore.</p><p>Not happy with the results? See the more detailed steps below.</p><h3>1. Creating the EC2 instance</h3><p>Create a new EC2 instance with the following characteristics:</p><ul><li><strong>AMI</strong>: Search for “deep learning” and choose a Deep Learning AMI from AWS. I am using <em>Deep Learning OSS Nvidia Driver AMI GPU PyTorch 2.0.1 (Amazon Linux 2)</em>. This image has all the tools and drivers we need.</li><li><strong>Instance type</strong>: I recommend using a G4 instance type with an Nvidia GPU (search for g4nd). I am using g4dn.2xlarge and the generation speed is about 1.30s/it.</li><li><strong>Storage</strong>: 45 GB should be enough for this example but consider increasing the size if you plan to download more models later on.</li></ul><h3>2. Installing Fooocus</h3><p>The next step is to install Fooocus, which is a tool based on Gradio which provides the UI needed to interact with the Stable Diffusion XL model and is optimized for image generation.</p><p>Open a terminal window and connect to the EC2 instance. I will use the AWSCloudShell.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*7PAN95F9kemeoj0NZ5KnJA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Jr8fJQkL-YvjJ0Y9hURP4w.png" /></figure><p>Clone the Fooocus Git repository:</p><pre>git clone https://github.com/lllyasviel/Fooocus.git</pre><p>Enter the Fooocus directory, create a Python virtual environment, activate it, and install all project dependencies:</p><pre>cd Fooocus<br>python3 -m venv fooocus_env<br>source fooocus_env/bin/activate<br>pip install -r requirements_versions.txt</pre><p>It may take a few minutes to install all dependencies but in the end, no errors should appear:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Vfbh9d6JZNBp6xQV6WUejQ.png" /></figure><p>Download the epiCPhotoGasm checkpoint which helps create better images.</p><pre>wget -P models/checkpoints/ https://civitai.com/api/download/models/223670 --content-disposition</pre><p>Next, while still being within the Python virtual environment, start Fooocus:</p><pre>python entry_with_update.py --share</pre><p>Initially, the base model needs to be downloaded, but the AWS infrastructure is quite fast and the 6GB will be downloaded in seconds. The base model used by Fooocus is Juggernaut XL (an SDXL model).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*uaSQEUaZyKM6AaXCkiSZIQ.png" /></figure><p>This will start a server locally but use Gradio as a proxy. Here is what they say about this: “Although the link is served through the Gradio Share Servers, these servers are only a proxy for your local server, and do not store any data sent through your app.” [5]</p><p>The address is visible in the logs printed in the console.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*G2C-L1hUEYYymNKxD1k-tQ.png" /></figure><p>Once you open the URL, the UI should look like this:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*paaML-DfLBzLx-O9T5Upww.png" /></figure><p>No, nothing is broken, it is really so minimalistic.</p><h3>3. Setting a password for the Fooocus UI (Gradio)</h3><p>Since Fooocus is now available to anyone knowing (or guessing) this address, let’s make a few security changes.</p><p>Stop the running process with Ctrl +C and configure authentication by creating the auth.json file:</p><pre>cp auth-example.json auth.json</pre><p>Use a text editor like Vim to open the auth.json file and change the default values for the username and password.</p><p>Restart the application and use the newly generated link:</p><pre>python entry_with_update.py --share</pre><p>Now you should see the login form. Use the credentials you have configured to log in.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YmYIdREU6Z_N6Fk0LzJVTg.png" /></figure><h3>4. Generating Aitana Lopez in Fooocus</h3><p>First, click on <em>Advanced</em> and then go to <em>Style</em> and make the same selections.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mRWMDaecJyjhh8WdlSO1RQ.png" /></figure><p>From the <em>Model</em> tab, select the refiner epicphotogasm_lastUnicorn.safetensors .</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nRaXTgYmxG5QYdFru2ak9Q.png" /></figure><p>Now go to the prompt and try the following:</p><pre>Adult female, full body, realistic, 35 years old, Spanish descent, Instagram yoga pose, wearing tank top, yoga pants, barefoot, bright neon pink hair, long, slightly curly, messy style, thin long face, V-shaped face, extremely slender build, small mole on left side of neck, skin imperfections, dark very thin eyebrows, one eyebrow raised, head tilted to the right, suspicious expression, dark brown eyes, medium breasts, no makeup.</pre><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JV99aXE_bc2wzKctvD-x4w.png" /></figure><blockquote>Researching &amp; writing this article took me quite a few hours. How long does it take you to <strong>press that 👏 a few times (up to 50 times)? </strong>Thank you for supporting me!</blockquote><h3>5. Terminate</h3><p>Okay, the fun is over. These GPU-intensive instances are quite expensive so once you are done playing, don’t forget to stop them. Btw, you are still paying for storage even if you stop the instance.</p><h3>Troubleshooting</h3><h4>You have requested more vCPU capacity than your current vCPU limit of 0 allows</h4><p>AWS imposes restrictions on the number and size of EC2 instances you can start. To raise these limits, a request must be filed with the AWS Support Center through a limit increase form.</p><h4>RuntimeError: No CUDA GPUs are available</h4><p>Ensure that the AWS instance type is <strong>g4nd</strong> which uses Nvidia GPUs and not <strong>g4ad</strong>, which uses AMD GPUs that require additional configuration.</p><h4>No interface is running right now</h4><p>You probably stopped or restarted the Fooocus UI. Check the logs for the URL.</p><h3>Conclusion</h3><p>I hope this article helped you better understand how to get a simple example running on AWS. Leave a comment in the section below if you have any questions. I would love to hear from you!</p><p><strong>Thank you for sticking with this article until the end. If you enjoyed it, please leave a comment, share, and press that 👏 a few times (up to 50 times). It will help others discover this information, and maybe it will help someone else as well.</strong></p><p><strong>Follow me on Medium and </strong><a href="https://www.youtube.com/channel/UCzAnXB3voQGeW-9Hi8X6vpg"><strong>YouTube</strong></a><strong> if you’re interested in more content like this one.</strong></p><h3>References</h3><p>[1] <a href="https://www.euronews.com/next/2023/12/02/meet-the-first-spanish-ai-model-earning-up-to-10000-per-month">https://www.euronews.com/next/2023/12/02/meet-the-first-spanish-ai-model-earning-up-to-10000-per-month</a></p><p>[2] <a href="https://www.instagram.com/fit_aitana/">https://www.instagram.com/fit_aitana/</a></p><p>[3] <a href="https://www.youtube.com/watch?v=ky5ZB-mqZKM">https://www.youtube.com/watch?v=ky5ZB-mqZKM</a></p><p>[4] <a href="https://aws.amazon.com/ec2/instance-types/g4/">https://aws.amazon.com/ec2/instance-types/g4/</a></p><p>[5] <a href="https://www.gradio.app/guides/sharing-your-app">https://www.gradio.app/guides/sharing-your-app</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5b7ff92e6765" width="1" height="1" alt=""><hr><p><a href="https://medium.com/valentine-ai/create-aitana-lopez-with-stable-diffusion-xl-running-on-the-aws-cloud-5b7ff92e6765">Create Aitana Lopez with Stable Diffusion XL Running on the AWS Cloud</a> was originally published in <a href="https://medium.com/valentine-ai">Valentine about AI</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>