**Created**:: [[2023-12-23 Saturday]] **Link**:: https://youtu.be/3G8hsV-V-gQ **Duration**:: 30:20 ![ExcaliAI Enhanced: More Visual Thinking Power](https://youtu.be/3G8hsV-V-gQ) # Summary In this video, Zsolt showcases the enhancements made to the ExcalAI Script for Obsidian Excalidraw, focusing on its capabilities for visual thinking and creativity. He presents various use cases including image generation from prompts, editing images, and generating mind maps, all powered by OpenAI's technology. The video also explains how users can install the script, set up their API key, and begin integrating these visual tools into their workflows. # Key Takeaways - ExcalAI integrates OpenAI's image generation into the Obsidian Excalidraw environment, providing powerful visual enhancement tools. - Users can generate images based on custom prompts, edit existing images, and create visual representations of quotes and ideas. - Setting up ExcalAI requires an OpenAI account and API key, and users should save generated images locally before they expire. # Content Hey everyone, Zsolt here. ExcalAI is a script available in the Obsidian Excalidraw script store, and today I'd like to show you the different enhancements I've made to the script over the last couple of weeks. First of all, we're going to look at a number of examples to showcase what ExcalAI is capable of. Then we're going to take a bit more structured look at the various use cases currently implemented. We're going to look under the hood just a little so you have an understanding of the logic flow of how to use ExcalAI, and finally, we're going to look at how you can install it, how you can set up your API key, and how you can get started with ExcalAI. So let's start with this example. [* ](https://youtu.be/3G8hsV-V-gQ?t=0) So I have this drawing here. I'm going to start ExcalAI right here, so it's in the Obsidian tools panel. If I scroll down here, you will find the robot here—that's ExcalAI. Because we are going to use this frequently today, I’m going to long press on this, and by long pressing on it, it was added here to the side panel so it's easier to access. Now I'm going to click on this, and here for the first example, I'm going to choose the model that I want to generate an image from, using an image and a prompt. Here, I'm going to just add "horror"; I think that's enough, so I want to create a horror image from this. Here I can set the size; I'm actually going to set this to be portrait. Here's an important notice I wanted to make: as this generates, note that the generation takes quite some time because this depends on OpenAI's response times. The note I wanted to make is that when the image is generated, you receive the image with a URL from OpenAI that will be deleted after 30 minutes. So, if you want to keep the image, then you will need to do the following: you will need to right-click on the image and choose "Save image from URL" to local file. When I do this, then the image is saved locally. Now take a look at what was generated; I think this is pretty cool! So first of all, you can actually see the tree, you can see the house with the red roof, you can see the road, you can see the flowers—or vice versa, in this case—and indeed, this is a horror image now. [* ](https://youtu.be/3G8hsV-V-gQ?t=30) What happens under the hood is I send this image to the vision interface of OpenAI and ask it to generate a detailed prompt. When the image is generated, this is the detailed prompt that OpenAI created, which was then sent to DALL-E for the image generation, and this is how we ended up with the image. Now let's just take a look at some of the examples we have. I’m going to pull this here and I'm going to put my horror image here, and let's just quickly look at the various styles that I created. So this was my sci-fi image, this is my fairy tale version, this is my mountain cabin version, this is my simple life version, Van Gogh minimalistic pencil version, the photo Unsplash, and the black-and-white photo version. I think these are all pretty cool, and of course in all of the cases, you can see how the house, the original pencil drawing that I created in Excalidraw on my phone, was translated here. [* ](https://youtu.be/3G8hsV-V-gQ?t=80) Now let's look at just another example here. So this is again an example of a city, and you can see here these were the various versions that were generated from this. I’m not going to spend the time now to generate them, but just to show you how this works. Now what I want to show you is how you can edit an image. This is my image edit use case right here. So you can see that I can add a mask over the picture. Now notice that the generated image is a square, and that is a limitation by OpenAI DALL-E that the image must be square-shaped. But here I can maybe change my prompt; I’m going to delete or just move my mask from there and I’m going to use these two masks on the side. I'm going to now select the image. I’m going to start ExcalAI, and I need to choose a different prompt. I'm now going to choose "Edit image." Now notice that when I click "Edit image," and maybe let me just click this back so you can see it, now you can see the image with the gray boxes around it. If I click "Edit image," then you will see that this suddenly turns into two. Now, this one right now maybe is not the ideal one; let me just put this back for a second so you can see what's going on. I'm going to again click "Edit image," and you can see here that the black areas are where the image is going to be created. This one right here is the same size as this one; it's just a bit because they are next to each other, you don’t see the mask, but of course, you can see the mask right here. And what I want to do to experiment with is—let's see—what if I say that this is a busy city street? This might not actually work so well; let’s see what OpenAI DALL-E is able to do with this, because of course, this image is not a busy city street, but maybe it is going to draw some houses on the side or something like that. I’m super curious how OpenAI is going to solve this problem for us, so let’s just wait until this generates. And, well, yeah, so this is not really perfect. So you can see that the busy city street thing appeared here, so my earlier approach with the spaceship flying saucer was better. But maybe we can do just one more experiment. You can see here I generated ports, and I’m going to take this image right here. I’m again going to click ExcalAI, and I'm going to write here “City Beach with lots of people.” So hopefully this is going to work out much better. Note that the generation can take up to 20 or 30 seconds, and wow, this is so cool! So you can see here our beach was created based on this image at the top, just a continuation of the image. I’m actually going to save this now. [* ](https://youtu.be/3G8hsV-V-gQ?t=180) So let’s now look at one more use case. The use case I want to look at is generating a prompt. By the way, notice that every time I generate an image, this message pops up just to remind you that if you want to keep the image, you need to save it. I’m going to close it now. I have this practice of creating a picture every day for a daily quote. This is a quote that I created this image for with MidJourney, so this is not ExcalAI and not DALL-E; this was my image generated for this quote “Do not ruin the present with the ruined past.” And I usually spend a good 10 to 20 minutes playing around until I get to an image that I really like. But right now, let’s see what happens if we automate this process. So I’m going to start ExcalAI, I’m going to choose "Generate an image to illustrate a quote," and I’m going to just paste here the quote. Now in the meantime, let me just give you a little bit of explanation. First of all, let me close this because I shouldn't have selected the text; I don’t want to send the image. So now it's only going to be the user prompt. So let me just walk you through what you see here on the screen. We have already looked at this drop-down list; this is where you can select the action. Each of the actions has a short help, so if you read it, hopefully that’s going to give you some better idea of what that prompt is about. I have a system prompt for most of the actions; you can read the system prompt here. You can also try to modify the system prompt. I played a bit with these system prompts so they generate the type of result I want. You can modify this as well if you want and see if you can come up with a better system prompt. And of course, here we have the user prompt, and here I can choose the size of the image I would like to see generated. So this is now going to be a portrait image. Note that if you configure DALL-E 2, we’ll look at configuration later, then the image sizes are going to be different. But right now, let’s just generate an image to illustrate this quote and let’s see how this image is going to look like. Now this is also something that happens sometimes—that there’s an unexpected error. No problem; we can run again, and usually the second time when you run the script, it executes. In the script, I’m not doing a serious amount of error handling, and as a result, you sometimes get that back. But again, this is just a reminder that as long as you see this generating spinner here, you know that I am waiting for the response from OpenAI because I print the image prompt here. This usually gives you an understanding of the logic behind why OpenAI thought that this would be a good illustration for the quote. So again, our quote was “Do not ruin the present with the ruined past.” So let’s read this: “Create an image featuring an otherworldly kaleidoscope-like landscape. The foreground includes a figure standing at a crossroads, their back to the viewer, exuding resilience. To their left, a path shows the past cluttered with fragments of broken objects and faded memories. To their right, the path is bright, leading to a vibrant and lively landscape. The figure’s outstretched arm reaches for the enriching future. Rich, contrasting colors should exude energy and optimism. The scene should blur reality and fantasy boundaries using light and shadow to symbolize a journey from past darkness to present light. The overall feeling should be hopeful, capturing the promise of embracing the present.” So I think with this explanation, this image is pretty good. The next one is going to be about creating a mind map to explain a whiteboard image. This was available in the earlier version of ExcalAI already. I made a little change that I want to show you here: you need to choose "Challenge my thinking" right there, and "Challenge my thinking" is going to generate a mind map. You can add a user prompt, or you can leave the prompt empty. I'm going to submit this. This is going to generate a mind map that partly summarizes the ideas on the image, partly adds additional ideas to it, and partly challenges the idea. So the image was—or the mind map was generated but wasn’t inserted, so there’s probably an issue with the script. And here’s what’s new: first of all, I inserted the Mermaid script here, and secondly here, if you open the menu and go to Mermaid to Excalidraw, you will find the script here and you can try to manually fix it. Unfortunately, OpenAI and ChatGPT sometimes result in incorrect formatting of the Mermaid diagram, so I’m going to just now click to clean this up. Probably this should be "subgraph" or something like that, but let’s look at how this looks like. I’m guessing that if I would type here...so let’s just undo the previous changes. So let’s just type in "subgraph" like this, and I’m going to type "end," and I’m going to just put this on my clipboard and replace these. So this unfortunately happens sometimes that ChatGPT generation of a Mermaid graph is not perfect. But the good thing is that you don’t need to regenerate it. Of course, you could also just simply press generate and create a new diagram, or you can come in here and edit it. The additional benefit of editing the graph is...and so there you go, it’s now created this graph that I can also change this to be from top down to maybe to be left right organized. Now if I insert this right here, then I can also use my script to select elements of type, and I’m going to select the arrows and here I can make the arrows sharp instead of rounded. I like this look of the mind map a little better. And now we can read what OpenAI returned to also how should we go about filling the page. This is the brick road approach to sketch noting, and this is the expansion of the concept. So this is an alternative to linear note-taking. And these two lines on top of are on top of each other, so I’m just going to bring this down here. And yeah, I’m not going to read through the material, but you can see here that there’s this analysis of my drawing. I can use this as a reflection on my thinking. I’m going to do this after recording this video, but I thought that this is a pretty interesting use case. The other example I want to show you is the code generation, which I think is more of just a game. I'm going to use this calculator right here, and I'm going to copy the prompt from here. And now I’m going to again start ExcalAI. I'm going to select here "Wireframe to code the new feature.” In this case, you can provide the description of the application you want to build as a user prompt, so it’s not part of the image. You could also add the text prompt under the image, and send it as an image, and then OpenAI would decode the text and generate probably the same calculator. This gives you some flexibility and options that now you can add a separate prompt. So let’s look at this calculator; it looks good. So let’s just see: 12 plus...let's maybe 5 times 6 equals 42. So the calculator actually works as expected! 2 over 1 is 0.5. So this is pretty good; I’m happy with the calculator. Also, in the description, I asked the calculator to follow the color scheme of the image, and indeed, I can see that this is largely the color scheme. I’m happy with the outcome. Now before we quickly recap the various functions and look under the hood how to use the tool, here’s one last example. So in this case, I took a photo from the internet and I added some icons from Flat icons here, and as GPT or rather DALL-E 2 created an image. So here’s the resulting image; I think this is pretty nice, and it’s a nice mix of using some icons from the internet as well as a picture to frame what I’m looking for. [* ](https://youtu.be/3G8hsV-V-gQ?t=540) With this, let's now just recap the different use cases. Altogether, there are three big areas of use cases. Well, you can play—and that’s the wireframe to code web development use case—you can create illustrations. And this reminds me there’s one more example we didn’t look at. So you can also create Excalidraw elements and convert elements to shapes, so let’s look at this. I’m going to draw this circle here; I’m going to select this. I’m going to select "Convert sketch to shapes." I’m going to delete my prompt, and let’s run this. This should be somewhat faster because here there’s no image generation. It was faster, but the end result is...well, not very good, so this was converted into a box. I mean, I thought that this was a circle, so it’s not perfect. Let’s look at the other use case. These two use cases about creating Excalidraw shapes are more of an experiment from my side; they are really not that good at the moment. But let’s create a smiley and see if the smiley is created. There’s our smiley! If I can get the smiley out of there, the smiley is actually pretty nice. I think that’s...I’m happy with the smiley part. They can also try others; I was successful with generating a car and a table and small things like that. But again, sometimes what’s generated, you need to remove background colors or make parts transparent because it’s hidden. It takes a bit of experimentation to work it out. But back to looking at the use cases: so web development and play. The other is generating Excalidraw elements, which is super experimental. Creating and editing images—we looked at a whole bunch of examples here. There are also additional use cases where you can just simply generate an image from a prompt. You can also use this for visual brainstorming. Maybe we can look at this example as well. So back to the brick road approach, the visual brainstorming is about creating an image. So I’m going to now choose "Visual brainstorm." I'm just going to send this image over and I’m going to click run. So the visual brainstorm creates a picture that somehow resonates with the content of the whiteboard that you’ve created. My idea is that looking at this picture and looking at the whiteboard can spark some additional ideas. So this is the image that was generated; this is about sketch noting for sure. We have the sketch note artist, we have this idea up here, we have a bit of a diagram up in this corner. It’s actually this leaf of ideas that are spreading all over. It's a nice illustration. Is it helping me think about sketch noting? Well, maybe it does. So I can reflect on this image and connect it with the ideas from the brick road approach to sketching, and just see some links. I’m actually going to save this image. So again, a final reminder that you need to save the image locally if you want to keep it; otherwise, you come back tomorrow, and this image is no longer going to be available. I think we've looked at all the use cases. So the other use case apart from illustrations is to generate new ideas. Generating new ideas could be an illustration of a quote, a visual brainstorm, or a Mermaid graph that illustrates an idea. [* ](https://youtu.be/3G8hsV-V-gQ?t=780) So then let's look at what's under the hood. I’m going to be very quick on this, but I think this is helpful, and you also saw how I’m using this in the presentation. So you need to select the elements you want to include in your prompt on the canvas. So for example, like this, I can select these elements, and then these are going to be the ones that I’m sending to OpenAI. For some of the prompts, like for example, for the quote, you don’t need to select elements because then you’re only sending the text prompt, and that’s okay. Then you choose the task. Now when you choose the task, then depending on the type of task, you saw that in case of selecting the "image edit," then the picture and the Excalidraw elements were taken in two separate parts. Remember, here we were looking at this mask, like that. And here if I start ExcalAI, you can see that in the normal case, this entire image would be sent to OpenAI. If I choose "Edit image," then this is split into two. I have the picture and I have the mask. Wherever the mask is black, that’s where the image is going to be generated. Maybe this can become much more visible if I do it here. Let me bring this to the front like this. And so, for example, if I wanted to change this house into a skyscraper, and then I would send—I would open ExcalAI like this—and then you can see here that this is where the skyscraper will go. You can see the mask and you can see the image. So depending on the task, you will see a different preview image: either the image plus the mask or the image only. You can then provide your text prompt and optionally modify the system prompt. So the system prompt is this one up here. In the case of the "Edit image," there is actually no system prompt, but in most of the cases, there are. This is the customize system prompt part. Then when you hit run at the bottom, then depending on the activity you selected, different things will happen. Either a Mermaid graph is generated, or an Excalidraw drawing is created, or a web app, or maybe DALL-E is executed, and an image is created in some cases. And this is the case when you create an image prompt, you want to add an image and a prompt and you want to create a new image based on that, inspired by that—like my little house. So this was all the examples of that. Then what happens is first I call GPT Vision, and GPT Vision generates an image prompt, and then with that, I go to DALL-E, and I generate the image. Finally, if you like the image, you should save it locally: right-click, save locally, or if not, then OpenAI will delete the image in 30 minutes. I’m not saving the images automatically to the vault because I’m assuming there’s going to be lots of rubbish generated by OpenAI, and you don’t want to clutter your vault. So this requires a bit of deliberate action on your side to save what you find locally. And finally, let’s look at what it takes to get started with this. So first of all, you need to install ExcalAI from the script library. How does it work? You click here to open the Obsidian tools panel, and top left, you see install or update Excalidraw scripts. If I open this, then I can search for ExcalAI like this. It will take me here; and if I click on this, then here I can just simply click install. Now it’s already installed, so I don’t need to install it, but this is how I would install it. If I click this, it will say installed ExcalAI. Once you have ExcalAI working, you need to go to OpenAI, and you need to create an account and add money to that account. This is the link you need to open, and you can see here that this is my balance; I have $392. By the way, generating images—we can look at how much today’s usage cost. So generating all the images we did right now, I was already I think at 9 cents. So today, this image generation for the video cost me about 40 cents. I don’t think it’s a huge amount of money, so you can see the usage information as well. Once you have your account and you’ve added money to the account, you need to add at least $5; otherwise, the GPT Vision model is not going to be available to you. If you have at least $5 in your account, you still need to wait about 10 to 20 minutes for OpenAI to activate your access. Then you can come here and configure in Obsidian. You need to create an OpenAI API key. You can see the link right here. If I click on this, it takes me to the API keys. I can click here to create a new secret key, and then the key is going to be created. Then I need to go to plug-in settings right here, and I need to click on Excalidraw AI settings. Here, I can configure my API key and my different models as well. Finally, when you're done, come here to the tools panel and find ExcalAI here amongst the downloaded scripts. If you long click on it, then you can add it and pin it to the side panel, and from then on, it’s going to work as I’ve demonstrated to you in the video. So that's all I wanted to share with you today. I already used it a lot in my workflows; I enjoy it so much! Yes, it costs a little money, but the amount is not so much, and I think the benefit you’re getting with the images, the mind maps, and the workflows is super valuable. Give it a try and let me know what you think in the comments below! Thank you. [* ](https://youtu.be/3G8hsV-V-gQ?t=1070) # YouTube Details ## YouTube Description 📽️ ✏️ Sign up for the Visual Thinking Workshop: https://www.visual-thinking-workshop.com/ ------ ExcaliAI Enhanced is a comprehensive walkthrough of all the ExcaliAI features, starting with image generation and image editing, through to code generation, generating simple Exalidraw shapes, and generating Mermaid diagrams. --- [00:00](https://youtu.be/3G8hsV-V-gQ?t=0) Intro [00:51](https://youtu.be/3G8hsV-V-gQ?t=51) Example 1: Generate an image based on a sketch [02:18](https://youtu.be/3G8hsV-V-gQ?t=138) Save the image locally [03:26](https://youtu.be/3G8hsV-V-gQ?t=206) Variations on the House theme [04:16](https://youtu.be/3G8hsV-V-gQ?t=256) City landscape example [04:39](https://youtu.be/3G8hsV-V-gQ?t=279) Image Editing with a Mask [07:19](https://youtu.be/3G8hsV-V-gQ?t=439) Image Editing 2nd Example: Extending the city with a beach [08:01](https://youtu.be/3G8hsV-V-gQ?t=481) Illustrating a quote [12:36](https://youtu.be/3G8hsV-V-gQ?t=756) Creating a Mermaid Graph [16:18](https://youtu.be/3G8hsV-V-gQ?t=978) Wireframe to Codeű [17:51](https://youtu.be/3G8hsV-V-gQ?t=1071) Generate images from pictures and icons [18:30](https://youtu.be/3G8hsV-V-gQ?t=1110) Recapping the features [18:53](https://youtu.be/3G8hsV-V-gQ?t=1133) Convert sketch to Excalidraw Elements [19:34](https://youtu.be/3G8hsV-V-gQ?t=1174) Generate an icon based on a prompt [20:58](https://youtu.be/3G8hsV-V-gQ?t=1258) Visual Brainstorm [22:53](https://youtu.be/3G8hsV-V-gQ?t=1373) Understanding the process of generation [27:05](https://youtu.be/3G8hsV-V-gQ?t=1625) Setting up ExcaliAI [29:51](https://youtu.be/3G8hsV-V-gQ?t=1791) Closing --- If you find my videos helpful, please say thanks by buying me a coffee: https://ko-fi.com/zsolt 📩 If you want to connect, you can reach me: (@zsviczian) on the Obsidian Members Group (OMG) on Discord, or on 🐦 Twitter: https://twitter.com/zsviczian --- 🍿Watch next: 📽️ Draw a UI https://youtu.be/y3kHl_6Ll4w Customize Embeddable Elements https://youtu.be/502swdqvZ2A Excalidraw Publish https://youtu.be/JC1E-jeiWhI Excalidraw Scripting https://youtu.be/OX5_UYjXEvc Golden Ratio script: https://youtu.be/2SHn_ruax-s ---- Visual Thinking Workshop: https://www.visual-thinking-workshop.com/ My blog: https://zsolt.blog/ Obsidian: https://obsidian.md Excalidraw-Obsidian: https://github.com/zsviczian/obsidian-excalidraw-plugin/ The script: https://github.com/zsviczian/obsidian-excalidraw-plugin/blob/master/ea-scripts/ExcaliAI.md ## YouTube Transcript [hey everyone jolt here exol AI is a](https://youtu.be/3G8hsV-V-gQ?t=0) [script available in the obsidian exol](https://youtu.be/3G8hsV-V-gQ?t=4) [draw script store and today I'd like to](https://youtu.be/3G8hsV-V-gQ?t=6) [show you the different enhancements I've](https://youtu.be/3G8hsV-V-gQ?t=10) [made to the script over the last couple](https://youtu.be/3G8hsV-V-gQ?t=12) [of weeks first of all we're going to](https://youtu.be/3G8hsV-V-gQ?t=15) [look at a number of examples to Showcase](https://youtu.be/3G8hsV-V-gQ?t=17) [what exol AI is capable of then we're](https://youtu.be/3G8hsV-V-gQ?t=21) [going to take a bit more structured look](https://youtu.be/3G8hsV-V-gQ?t=25) [at the various use cases currently in](https://youtu.be/3G8hsV-V-gQ?t=27) [implemented we're going to look under](https://youtu.be/3G8hsV-V-gQ?t=30) [the hood just a little so you have an](https://youtu.be/3G8hsV-V-gQ?t=32) [understanding of the logic flow of how](https://youtu.be/3G8hsV-V-gQ?t=36) [to use exol Ai and finally we're going](https://youtu.be/3G8hsV-V-gQ?t=39) [to look at how you can install it how](https://youtu.be/3G8hsV-V-gQ?t=42) [you can set up your API key and how you](https://youtu.be/3G8hsV-V-gQ?t=45) [can get started with excal AI so let's](https://youtu.be/3G8hsV-V-gQ?t=48) [start with this example so I have this](https://youtu.be/3G8hsV-V-gQ?t=51) [drawing here I'm going to start exol AI](https://youtu.be/3G8hsV-V-gQ?t=54) [right here so it's in the obsidian tools](https://youtu.be/3G8hsV-V-gQ?t=58) [panel and if I scroll down here you will](https://youtu.be/3G8hsV-V-gQ?t=60) [find the robot here that's xol AI](https://youtu.be/3G8hsV-V-gQ?t=64) [because we are going to use this](https://youtu.be/3G8hsV-V-gQ?t=67) [frequently today I'm going to long press](https://youtu.be/3G8hsV-V-gQ?t=69) [on this and by long pressing on it it](https://youtu.be/3G8hsV-V-gQ?t=71) [was added here to the side panel so it's](https://youtu.be/3G8hsV-V-gQ?t=75) [easier to access and now I'm going to](https://youtu.be/3G8hsV-V-gQ?t=77) [click on this and here for the first](https://youtu.be/3G8hsV-V-gQ?t=80) [example I'm going to choose the model](https://youtu.be/3G8hsV-V-gQ?t=83) [that I want to generate an image from](https://youtu.be/3G8hsV-V-gQ?t=87) [from an image and a prompt and here I'm](https://youtu.be/3G8hsV-V-gQ?t=89) [going to just add](https://youtu.be/3G8hsV-V-gQ?t=93) [horror I think that's enough so I want](https://youtu.be/3G8hsV-V-gQ?t=96) [to create a horror image of this here I](https://youtu.be/3G8hsV-V-gQ?t=99) [can set the size I'm actually going to](https://youtu.be/3G8hsV-V-gQ?t=103) [set this to be portrait and here's an](https://youtu.be/3G8hsV-V-gQ?t=106) [important notice that I'm going to](https://youtu.be/3G8hsV-V-gQ?t=109) [explain as this generates note the](https://youtu.be/3G8hsV-V-gQ?t=111) [generation takes quite some time because](https://youtu.be/3G8hsV-V-gQ?t=115) [this depends deps on open AI response](https://youtu.be/3G8hsV-V-gQ?t=119) [times the note I wanted to make is when](https://youtu.be/3G8hsV-V-gQ?t=121) [the image is generated you receive the](https://youtu.be/3G8hsV-V-gQ?t=125) [image with a URL from open AI that URL](https://youtu.be/3G8hsV-V-gQ?t=128) [is going to be deleted after 30 minutes](https://youtu.be/3G8hsV-V-gQ?t=133) [so if you want to keep the image then](https://youtu.be/3G8hsV-V-gQ?t=138) [you will need to do the following you](https://youtu.be/3G8hsV-V-gQ?t=140) [will need to right click on the image](https://youtu.be/3G8hsV-V-gQ?t=143) [and you need to choose save image from](https://youtu.be/3G8hsV-V-gQ?t=146) [your L to local file when I do this then](https://youtu.be/3G8hsV-V-gQ?t=149) [the image was saved locally now take a](https://youtu.be/3G8hsV-V-gQ?t=153) [look at what was generated I think this](https://youtu.be/3G8hsV-V-gQ?t=157) [is pretty cool so first of all you can](https://youtu.be/3G8hsV-V-gQ?t=160) [actually see the tree you can see the](https://youtu.be/3G8hsV-V-gQ?t=163) [house with the Red Roof you can see the](https://youtu.be/3G8hsV-V-gQ?t=165) [road you can see the flowers or vs in](https://youtu.be/3G8hsV-V-gQ?t=169) [this case and indeed this is a horror](https://youtu.be/3G8hsV-V-gQ?t=174) [image now](https://youtu.be/3G8hsV-V-gQ?t=178) [what happens under the hood is I send](https://youtu.be/3G8hsV-V-gQ?t=180) [this image to the vision interface of](https://youtu.be/3G8hsV-V-gQ?t=184) [open Ai and ask it to generate a](https://youtu.be/3G8hsV-V-gQ?t=187) [detailed prompt and so when the image is](https://youtu.be/3G8hsV-V-gQ?t=190) [generated this is the detailed prompt](https://youtu.be/3G8hsV-V-gQ?t=193) [that openai created which was then sent](https://youtu.be/3G8hsV-V-gQ?t=196) [to doll e for the image generation and](https://youtu.be/3G8hsV-V-gQ?t=200) [this is how we ended up with the image](https://youtu.be/3G8hsV-V-gQ?t=203) [now let's just take a look at some of](https://youtu.be/3G8hsV-V-gQ?t=206) [the examples we have so I'm going to](https://youtu.be/3G8hsV-V-gQ?t=208) [pull this here and I'm going to put my](https://youtu.be/3G8hsV-V-gQ?t=211) [horror image here and let's just quickly](https://youtu.be/3G8hsV-V-gQ?t=213) [look at the various styles that I](https://youtu.be/3G8hsV-V-gQ?t=216) [created so this was my sci-fi image this](https://youtu.be/3G8hsV-V-gQ?t=219) [is my fairy tale version this is my](https://youtu.be/3G8hsV-V-gQ?t=222) [mountain cabin version this is my simple](https://youtu.be/3G8hsV-V-gQ?t=225) [life version vangog minimalistic pencil](https://youtu.be/3G8hsV-V-gQ?t=228) [version the photo unsplash and the black](https://youtu.be/3G8hsV-V-gQ?t=232) [and white photo version I think these](https://youtu.be/3G8hsV-V-gQ?t=236) [are all pretty cool and of course in all](https://youtu.be/3G8hsV-V-gQ?t=237) [of the cases you can see how the house](https://youtu.be/3G8hsV-V-gQ?t=241) [the original pencil drawing that I](https://youtu.be/3G8hsV-V-gQ?t=245) [created in exol draw on my phone was](https://youtu.be/3G8hsV-V-gQ?t=247) [translated here now let's look at just](https://youtu.be/3G8hsV-V-gQ?t=252) [another example here so this is again an](https://youtu.be/3G8hsV-V-gQ?t=255) [example here of a city and you can see](https://youtu.be/3G8hsV-V-gQ?t=259) [here these were the various versions](https://youtu.be/3G8hsV-V-gQ?t=262) [that were generated from this I'm not](https://youtu.be/3G8hsV-V-gQ?t=265) [going to spend the time now to generate](https://youtu.be/3G8hsV-V-gQ?t=268) [them but just to show you how this works](https://youtu.be/3G8hsV-V-gQ?t=270) [now what I want to show you is how you](https://youtu.be/3G8hsV-V-gQ?t=273) [can edit an image so this is my image](https://youtu.be/3G8hsV-V-gQ?t=276) [edit use case right here so you can see](https://youtu.be/3G8hsV-V-gQ?t=281) [that I can add a mask over the picture](https://youtu.be/3G8hsV-V-gQ?t=285) [now notice that the generated image is a](https://youtu.be/3G8hsV-V-gQ?t=288) [square and that is a limitation by open](https://youtu.be/3G8hsV-V-gQ?t=292) [AI dolly that the image must be squar](https://youtu.be/3G8hsV-V-gQ?t=296) [shaped but here I can maybe change now](https://youtu.be/3G8hsV-V-gQ?t=300) [my prompt I'm going to delete or just](https://youtu.be/3G8hsV-V-gQ?t=303) [move my mask from there and I'm going to](https://youtu.be/3G8hsV-V-gQ?t=307) [use these two masks on the side and I'm](https://youtu.be/3G8hsV-V-gQ?t=310) [going to now select the image I'm going](https://youtu.be/3G8hsV-V-gQ?t=314) [to start excal Ai and I need to choose a](https://youtu.be/3G8hsV-V-gQ?t=317) [different prompt I'm now going to choose](https://youtu.be/3G8hsV-V-gQ?t=321) [edit image now notice that when I click](https://youtu.be/3G8hsV-V-gQ?t=324) [edit image and maybe let me just click](https://youtu.be/3G8hsV-V-gQ?t=327) [this back so you can see it now you can](https://youtu.be/3G8hsV-V-gQ?t=331) [see the image with the gray boxes around](https://youtu.be/3G8hsV-V-gQ?t=334) [it if I click edit image then you will](https://youtu.be/3G8hsV-V-gQ?t=337) [see that this suddenly turns into two](https://youtu.be/3G8hsV-V-gQ?t=342) [now it this one right now maybe is not](https://youtu.be/3G8hsV-V-gQ?t=344) [the ideal one let me just put this back](https://youtu.be/3G8hsV-V-gQ?t=347) [here for a second so you can see what's](https://youtu.be/3G8hsV-V-gQ?t=350) [going on I'm going to again click edit](https://youtu.be/3G8hsV-V-gQ?t=352) [image and you can see here that the](https://youtu.be/3G8hsV-V-gQ?t=356) [black areas are where the image is going](https://youtu.be/3G8hsV-V-gQ?t=359) [to be created this one right here is the](https://youtu.be/3G8hsV-V-gQ?t=362) [same size as this one it's just a bit](https://youtu.be/3G8hsV-V-gQ?t=366) [because they are next to each other you](https://youtu.be/3G8hsV-V-gQ?t=369) [don't see the mask but of course you can](https://youtu.be/3G8hsV-V-gQ?t=371) [see the mask right here and what I want](https://youtu.be/3G8hsV-V-gQ?t=373) [to do to experiment with is let's see](https://youtu.be/3G8hsV-V-gQ?t=376) [what if I say that this is a busy City](https://youtu.be/3G8hsV-V-gQ?t=381) [street so this might not actually work](https://youtu.be/3G8hsV-V-gQ?t=387) [so well let's see what open AI doly is](https://youtu.be/3G8hsV-V-gQ?t=390) [able to do this with this because of](https://youtu.be/3G8hsV-V-gQ?t=394) [course this](https://youtu.be/3G8hsV-V-gQ?t=396) [image is not a busy City street but](https://youtu.be/3G8hsV-V-gQ?t=397) [maybe it is going to draw some houses on](https://youtu.be/3G8hsV-V-gQ?t=401) [the side or something like that I'm](https://youtu.be/3G8hsV-V-gQ?t=404) [super curious how open AI is going to](https://youtu.be/3G8hsV-V-gQ?t=407) [solve this problem for us so let's just](https://youtu.be/3G8hsV-V-gQ?t=411) [wait until this](https://youtu.be/3G8hsV-V-gQ?t=415) [generates and well well yeah so this is](https://youtu.be/3G8hsV-V-gQ?t=417) [not really perfect so you can see the](https://youtu.be/3G8hsV-V-gQ?t=422) [busy City street this thing appeared](https://youtu.be/3G8hsV-V-gQ?t=424) [here so my earlier approach with the uh](https://youtu.be/3G8hsV-V-gQ?t=428) [space ship Flying Saucer was better but](https://youtu.be/3G8hsV-V-gQ?t=432) [maybe we can do just one more experiment](https://youtu.be/3G8hsV-V-gQ?t=435) [you can see here I generated ports here](https://youtu.be/3G8hsV-V-gQ?t=438) [so I'm going to take this image right](https://youtu.be/3G8hsV-V-gQ?t=442) [here I'm again going to click exol AI](https://youtu.be/3G8hsV-V-gQ?t=445) [and I'm going to write here City Beach](https://youtu.be/3G8hsV-V-gQ?t=449) [with lots of people so hopefully this is](https://youtu.be/3G8hsV-V-gQ?t=454) [going to work out much better note the](https://youtu.be/3G8hsV-V-gQ?t=458) [generation can take up to 20 30 seconds](https://youtu.be/3G8hsV-V-gQ?t=462) [and wow this is so cool so you can see](https://youtu.be/3G8hsV-V-gQ?t=465) [here our beach was created based on this](https://youtu.be/3G8hsV-V-gQ?t=468) [image at the top just a continuation of](https://youtu.be/3G8hsV-V-gQ?t=472) [the image I'm actually going to save](https://youtu.be/3G8hsV-V-gQ?t=475) [this so let's now look at one more use](https://youtu.be/3G8hsV-V-gQ?t=477) [case the use case I want to look at is](https://youtu.be/3G8hsV-V-gQ?t=480) [generating a prompt by the way notice](https://youtu.be/3G8hsV-V-gQ?t=484) [that every time I generate an image this](https://youtu.be/3G8hsV-V-gQ?t=486) [message pops up just to remind you that](https://youtu.be/3G8hsV-V-gQ?t=489) [if you want to keep the image you need](https://youtu.be/3G8hsV-V-gQ?t=492) [to save it I'm going to close it now I](https://youtu.be/3G8hsV-V-gQ?t=494) [have this practice of](https://youtu.be/3G8hsV-V-gQ?t=497) [creating a picture every day for a daily](https://youtu.be/3G8hsV-V-gQ?t=499) [quote so this is a quote that I created](https://youtu.be/3G8hsV-V-gQ?t=504) [this image for with mid Journey so this](https://youtu.be/3G8hsV-V-gQ?t=507) [is not excit and not Dolly this was my](https://youtu.be/3G8hsV-V-gQ?t=510) [image generated for this quot to at Mid](https://youtu.be/3G8hsV-V-gQ?t=515) [journey and I usually spend good 10 20](https://youtu.be/3G8hsV-V-gQ?t=517) [minutes playing around until I get to an](https://youtu.be/3G8hsV-V-gQ?t=521) [image that I really like but right now](https://youtu.be/3G8hsV-V-gQ?t=524) [let's see what happens if we automate](https://youtu.be/3G8hsV-V-gQ?t=527) [this process so I'm going to start exol](https://youtu.be/3G8hsV-V-gQ?t=529) [AI I'm going to choose the generate an](https://youtu.be/3G8hsV-V-gQ?t=532) [image to illustrate a quote and I'm](https://youtu.be/3G8hsV-V-gQ?t=536) [going to just paste here the quote now](https://youtu.be/3G8hsV-V-gQ?t=539) [in the meantime let me just give you a](https://youtu.be/3G8hsV-V-gQ?t=542) [little bit of explanation first of all](https://youtu.be/3G8hsV-V-gQ?t=546) [let me close this because I shouldn't](https://youtu.be/3G8hsV-V-gQ?t=550) [have selected the text I don't want to](https://youtu.be/3G8hsV-V-gQ?t=552) [send the image so now it's only going to](https://youtu.be/3G8hsV-V-gQ?t=555) [be the user prompt so let me just walk](https://youtu.be/3G8hsV-V-gQ?t=557) [you through what you see here on the](https://youtu.be/3G8hsV-V-gQ?t=560) [screen we have already looked at this](https://youtu.be/3G8hsV-V-gQ?t=563) [drop- down list this is where you can](https://youtu.be/3G8hsV-V-gQ?t=566) [select the action each of the actions](https://youtu.be/3G8hsV-V-gQ?t=568) [has a short help so if you read it](https://youtu.be/3G8hsV-V-gQ?t=572) [hopefully that's going to give you some](https://youtu.be/3G8hsV-V-gQ?t=575) [better idea of what that prompt is about](https://youtu.be/3G8hsV-V-gQ?t=577) [I have a system prompt for most of the](https://youtu.be/3G8hsV-V-gQ?t=581) [actions you can read the system prompt](https://youtu.be/3G8hsV-V-gQ?t=584) [here you can also try to modify the](https://youtu.be/3G8hsV-V-gQ?t=587) [system prompt I played a bit with these](https://youtu.be/3G8hsV-V-gQ?t=590) [system prompts so they generate the type](https://youtu.be/3G8hsV-V-gQ?t=594) [of result I want you can move modify](https://youtu.be/3G8hsV-V-gQ?t=596) [this as well if you want and see if you](https://youtu.be/3G8hsV-V-gQ?t=599) [can come up with a better system prompt](https://youtu.be/3G8hsV-V-gQ?t=603) [and of course here we have the user](https://youtu.be/3G8hsV-V-gQ?t=605) [prompt and here I can choose the size of](https://youtu.be/3G8hsV-V-gQ?t=607) [the image I would like to see generated](https://youtu.be/3G8hsV-V-gQ?t=610) [so this is now going to be a portrait](https://youtu.be/3G8hsV-V-gQ?t=613) [image note that if you configure Dolly 2](https://youtu.be/3G8hsV-V-gQ?t=616) [we'll look at configuration later then](https://youtu.be/3G8hsV-V-gQ?t=620) [the image sizes are going to be](https://youtu.be/3G8hsV-V-gQ?t=622) [different but right now let's just](https://youtu.be/3G8hsV-V-gQ?t=624) [generate an image to illustrate this](https://youtu.be/3G8hsV-V-gQ?t=627) [quote and let's see how this image is](https://youtu.be/3G8hsV-V-gQ?t=630) [going to look like now this is also](https://youtu.be/3G8hsV-V-gQ?t=633) [something that happens sometimes that](https://youtu.be/3G8hsV-V-gQ?t=636) [there's an unexpected error no problem](https://youtu.be/3G8hsV-V-gQ?t=638) [we can run again and usually the second](https://youtu.be/3G8hsV-V-gQ?t=642) [time when you run the script it executes](https://youtu.be/3G8hsV-V-gQ?t=645) [in the script I'm not doing serious](https://youtu.be/3G8hsV-V-gQ?t=649) [amount of airor handling and as a result](https://youtu.be/3G8hsV-V-gQ?t=652) [you sometimes get that back but again](https://youtu.be/3G8hsV-V-gQ?t=655) [this is just a reminder that as long as](https://youtu.be/3G8hsV-V-gQ?t=658) [you see this generating spinner here you](https://youtu.be/3G8hsV-V-gQ?t=660) [know that I am waiting for the response](https://youtu.be/3G8hsV-V-gQ?t=664) [from open AI because I print the image](https://youtu.be/3G8hsV-V-gQ?t=668) [prompt here this usually gives you an](https://youtu.be/3G8hsV-V-gQ?t=671) [understanding of the logic why open AI](https://youtu.be/3G8hsV-V-gQ?t=674) [thought that this would be a good](https://youtu.be/3G8hsV-V-gQ?t=677) [illustration for the quote so again our](https://youtu.be/3G8hsV-V-gQ?t=679) [quote was don't ruin the present with](https://youtu.be/3G8hsV-V-gQ?t=682) [the ruined past so let's read this](https://youtu.be/3G8hsV-V-gQ?t=685) [create an image featuring an](https://youtu.be/3G8hsV-V-gQ?t=689) [otherworldly collidoscope like landscape](https://youtu.be/3G8hsV-V-gQ?t=690) [the foreground includes a figure](https://youtu.be/3G8hsV-V-gQ?t=693) [standing at a Crossroads their back to](https://youtu.be/3G8hsV-V-gQ?t=696) [the viewer exuding](https://youtu.be/3G8hsV-V-gQ?t=699) [resilience to their left a path showing](https://youtu.be/3G8hsV-V-gQ?t=701) [the past cluttered with fragments of](https://youtu.be/3G8hsV-V-gQ?t=705) [broken objects and Faded memories to](https://youtu.be/3G8hsV-V-gQ?t=708) [their right the path is bright leading](https://youtu.be/3G8hsV-V-gQ?t=712) [to a vibrant and Lively landscape the](https://youtu.be/3G8hsV-V-gQ?t=715) [figure 's outstretched arm reaches for](https://youtu.be/3G8hsV-V-gQ?t=718) [the enriching future Rich contrasting](https://youtu.be/3G8hsV-V-gQ?t=721) [colors should exude energy and optimism](https://youtu.be/3G8hsV-V-gQ?t=725) [the scene should blur reality and](https://youtu.be/3G8hsV-V-gQ?t=729) [fantasy boundaries using light and](https://youtu.be/3G8hsV-V-gQ?t=731) [Shadow to symbolize a journey from past](https://youtu.be/3G8hsV-V-gQ?t=734) [Darkness to present light the overall](https://youtu.be/3G8hsV-V-gQ?t=737) [feeling should be hopeful capturing the](https://youtu.be/3G8hsV-V-gQ?t=741) [promise of embracing the](https://youtu.be/3G8hsV-V-gQ?t=743) [present so I think with this](https://youtu.be/3G8hsV-V-gQ?t=746) [explanation this image is pretty good](https://youtu.be/3G8hsV-V-gQ?t=749) [the next one is going to be about](https://youtu.be/3G8hsV-V-gQ?t=753) [creating a mind map to explain a](https://youtu.be/3G8hsV-V-gQ?t=756) [whiteboard image this was available in](https://youtu.be/3G8hsV-V-gQ?t=759) [the earlier version of exol AI already I](https://youtu.be/3G8hsV-V-gQ?t=762) [made a little change that I want to show](https://youtu.be/3G8hsV-V-gQ?t=766) [you here you need to choose challenge my](https://youtu.be/3G8hsV-V-gQ?t=768) [thinking right there and challenge my](https://youtu.be/3G8hsV-V-gQ?t=773) [thinking is going to generate a mind map](https://youtu.be/3G8hsV-V-gQ?t=775) [you can add a user prompt or you can](https://youtu.be/3G8hsV-V-gQ?t=779) [leave the prompt empty going to submit](https://youtu.be/3G8hsV-V-gQ?t=782) [this this is going to generate a mind](https://youtu.be/3G8hsV-V-gQ?t=785) [map that partly summarizes the ideas on](https://youtu.be/3G8hsV-V-gQ?t=788) [the image partly adds additional ideas](https://youtu.be/3G8hsV-V-gQ?t=792) [to it and partly challenges the idea so](https://youtu.be/3G8hsV-V-gQ?t=796) [the image was or the Mind map was](https://youtu.be/3G8hsV-V-gQ?t=800) [generated but wasn't inserted so there's](https://youtu.be/3G8hsV-V-gQ?t=803) [probably an issue with the script and](https://youtu.be/3G8hsV-V-gQ?t=807) [here's what's new so first of all I](https://youtu.be/3G8hsV-V-gQ?t=810) [inserted the mermaid script here and](https://youtu.be/3G8hsV-V-gQ?t=812) [secondly here if you open the menu and](https://youtu.be/3G8hsV-V-gQ?t=815) [go to mermaid to exol draw you will find](https://youtu.be/3G8hsV-V-gQ?t=817) [the script here and you can try to](https://youtu.be/3G8hsV-V-gQ?t=821) [manually fix it unfortunately open AI CH](https://youtu.be/3G8hsV-V-gQ?t=824) [GPT sometimes results in incorrect](https://youtu.be/3G8hsV-V-gQ?t=829) [formatting of mermaid diagram so I'm](https://youtu.be/3G8hsV-V-gQ?t=833) [going to just now click clean this up](https://youtu.be/3G8hsV-V-gQ?t=836) [probably this should be subgraph or](https://youtu.be/3G8hsV-V-gQ?t=839) [something like that but let's look at](https://youtu.be/3G8hsV-V-gQ?t=842) [how this looks like I'm guessing that if](https://youtu.be/3G8hsV-V-gQ?t=844) [I would type here so let's just undo the](https://youtu.be/3G8hsV-V-gQ?t=847) [previous changes so let's just type in](https://youtu.be/3G8hsV-V-gQ?t=850) [subgraph like this and I'm going to type](https://youtu.be/3G8hsV-V-gQ?t=852) [end and I'm going to just put this on my](https://youtu.be/3G8hsV-V-gQ?t=856) [clipboard and replace these so this](https://youtu.be/3G8hsV-V-gQ?t=860) [unfortunately happens sometimes that ch](https://youtu.be/3G8hsV-V-gQ?t=863) [gbt](https://youtu.be/3G8hsV-V-gQ?t=868) [generation of a mermaid graph is not](https://youtu.be/3G8hsV-V-gQ?t=869) [perfect but the good thing is that you](https://youtu.be/3G8hsV-V-gQ?t=872) [don't need to regenerated of course you](https://youtu.be/3G8hsV-V-gQ?t=875) [could also just simply press generate](https://youtu.be/3G8hsV-V-gQ?t=878) [and create a new cph or you can come in](https://youtu.be/3G8hsV-V-gQ?t=880) [here and you can edit it the additional](https://youtu.be/3G8hsV-V-gQ?t=883) [benefit of editing the graph is and so](https://youtu.be/3G8hsV-V-gQ?t=887) [there you go it's now created this graph](https://youtu.be/3G8hsV-V-gQ?t=891) [that I can also change this to be from](https://youtu.be/3G8hsV-V-gQ?t=894) [instead of top down maybe to be left](https://youtu.be/3G8hsV-V-gQ?t=897) [right organized and now if I insert this](https://youtu.be/3G8hsV-V-gQ?t=901) [right here then I can also use my script](https://youtu.be/3G8hsV-V-gQ?t=905) [select elements of type and I'm going to](https://youtu.be/3G8hsV-V-gQ?t=910) [select the](https://youtu.be/3G8hsV-V-gQ?t=913) [arrows and here I can make the arrows to](https://youtu.be/3G8hsV-V-gQ?t=914) [be sharp instead of](https://youtu.be/3G8hsV-V-gQ?t=917) [rounded I like this look of the Mind map](https://youtu.be/3G8hsV-V-gQ?t=920) [a little better and now we can read what](https://youtu.be/3G8hsV-V-gQ?t=923) [open AI returned to also how should we](https://youtu.be/3G8hsV-V-gQ?t=927) [go about filling the page and this is](https://youtu.be/3G8hsV-V-gQ?t=930) [the brick road approach to sketch noting](https://youtu.be/3G8hsV-V-gQ?t=932) [and this is the expansion of the concept](https://youtu.be/3G8hsV-V-gQ?t=935) [so this is an alternative to linear note](https://youtu.be/3G8hsV-V-gQ?t=940) [taking and these two lines on top of are](https://youtu.be/3G8hsV-V-gQ?t=944) [on top of each other so I'm just going](https://youtu.be/3G8hsV-V-gQ?t=947) [to bring this down here and yeah I'm not](https://youtu.be/3G8hsV-V-gQ?t=948) [going to read through the material but](https://youtu.be/3G8hsV-V-gQ?t=953) [you can see here that there's this](https://youtu.be/3G8hsV-V-gQ?t=955) [analysis of my drawing I can use this as](https://youtu.be/3G8hsV-V-gQ?t=959) [a reflection on my thinking I'm going to](https://youtu.be/3G8hsV-V-gQ?t=962) [do this after recording this video but I](https://youtu.be/3G8hsV-V-gQ?t=966) [thought that this is a pretty](https://youtu.be/3G8hsV-V-gQ?t=968) [interesting use case the other example I](https://youtu.be/3G8hsV-V-gQ?t=971) [want to show you is the code generation](https://youtu.be/3G8hsV-V-gQ?t=974) [which I think is more of just a game I'm](https://youtu.be/3G8hsV-V-gQ?t=977) [going to use this calculator right here](https://youtu.be/3G8hsV-V-gQ?t=982) [and I'm going to copy the prompt from](https://youtu.be/3G8hsV-V-gQ?t=984) [here and now I'm going to again start](https://youtu.be/3G8hsV-V-gQ?t=988) [exol AI I'm going to select here](https://youtu.be/3G8hsV-V-gQ?t=991) [wireframe to code the new feature in](https://youtu.be/3G8hsV-V-gQ?t=994) [this case is you can provide the](https://youtu.be/3G8hsV-V-gQ?t=998) [description of the application you want](https://youtu.be/3G8hsV-V-gQ?t=1000) [to build as a user prompt so it's not](https://youtu.be/3G8hsV-V-gQ?t=1003) [part of the image so you could also add](https://youtu.be/3G8hsV-V-gQ?t=1006) [the text prompt under the image and send](https://youtu.be/3G8hsV-V-gQ?t=1009) [it as an image and then open AI would](https://youtu.be/3G8hsV-V-gQ?t=1011) [decode the text and generate probably](https://youtu.be/3G8hsV-V-gQ?t=1014) [the same](https://youtu.be/3G8hsV-V-gQ?t=1018) [calculator this gives you some](https://youtu.be/3G8hsV-V-gQ?t=1019) [flexibility and options that now you can](https://youtu.be/3G8hsV-V-gQ?t=1021) [add a separate prompt so let's look at](https://youtu.be/3G8hsV-V-gQ?t=1024) [this calculator it looks good so let's](https://youtu.be/3G8hsV-V-gQ?t=1027) [just see 12 plus let's maybe 5 *](https://youtu.be/3G8hsV-V-gQ?t=1030) [6 equal 42 so the calculator actually](https://youtu.be/3G8hsV-V-gQ?t=1036) [works as expected 2 over one is 0.5 so](https://youtu.be/3G8hsV-V-gQ?t=1042) [this is this is pretty good I'm I'm](https://youtu.be/3G8hsV-V-gQ?t=1046) [pretty happy with the calculator also in](https://youtu.be/3G8hsV-V-gQ?t=1049) [the description I asked the calculator](https://youtu.be/3G8hsV-V-gQ?t=1051) [to follow the color scheme of the image](https://youtu.be/3G8hsV-V-gQ?t=1055) [and indeed I can see that this is](https://youtu.be/3G8hsV-V-gQ?t=1058) [largely the color scheme I'm happy with](https://youtu.be/3G8hsV-V-gQ?t=1060) [the outcome and now before we quickly](https://youtu.be/3G8hsV-V-gQ?t=1063) [recap the various functions and look](https://youtu.be/3G8hsV-V-gQ?t=1066) [under the hood how to use the tool](https://youtu.be/3G8hsV-V-gQ?t=1069) [here's one last example so in this case](https://youtu.be/3G8hsV-V-gQ?t=1071) [I took a photo from the internet and I](https://youtu.be/3G8hsV-V-gQ?t=1074) [added some](https://youtu.be/3G8hsV-V-gQ?t=1077) [icons from Flat icons here and](https://youtu.be/3G8hsV-V-gQ?t=1078) [as C GPT or rather Dolly to create an](https://youtu.be/3G8hsV-V-gQ?t=1082) [image so here's the resulting image I](https://youtu.be/3G8hsV-V-gQ?t=1088) [think this is uh pretty nice and it's a](https://youtu.be/3G8hsV-V-gQ?t=1091) [nice mix of using some icons from the](https://youtu.be/3G8hsV-V-gQ?t=1094) [internet as well as a picture to frame](https://youtu.be/3G8hsV-V-gQ?t=1097) [what I'm looking for and then GPT can](https://youtu.be/3G8hsV-V-gQ?t=1101) [generate the image for us so with this](https://youtu.be/3G8hsV-V-gQ?t=1104) [let's now just recap the different use](https://youtu.be/3G8hsV-V-gQ?t=1107) [cases so alt together there are three](https://youtu.be/3G8hsV-V-gQ?t=1110) [big areas of use cases well you can play](https://youtu.be/3G8hsV-V-gQ?t=1114) [and that's the wireframe to code web](https://youtu.be/3G8hsV-V-gQ?t=1118) [development use case you can create](https://youtu.be/3G8hsV-V-gQ?t=1120) [illustrations and this reminds me](https://youtu.be/3G8hsV-V-gQ?t=1125) [there's one more example we didn't look](https://youtu.be/3G8hsV-V-gQ?t=1127) [at so you can also create excital](https://youtu.be/3G8hsV-V-gQ?t=1130) [elements and convert elements to shapes](https://youtu.be/3G8hsV-V-gQ?t=1132) [so let's look at this I'm going to draw](https://youtu.be/3G8hsV-V-gQ?t=1135) [this circle here I'm going to select](https://youtu.be/3G8hsV-V-gQ?t=1138) [this I'm going to select convert sketch](https://youtu.be/3G8hsV-V-gQ?t=1142) [to shapes I'm going to delete my prompt](https://youtu.be/3G8hsV-V-gQ?t=1145) [and let's run this this should be](https://youtu.be/3G8hsV-V-gQ?t=1150) [somewhat faster because here there's no](https://youtu.be/3G8hsV-V-gQ?t=1152) [image](https://youtu.be/3G8hsV-V-gQ?t=1155) [Generation Um it was faster but the end](https://youtu.be/3G8hsV-V-gQ?t=1156) [result is well not very good so this was](https://youtu.be/3G8hsV-V-gQ?t=1160) [converted into a box I mean I thought](https://youtu.be/3G8hsV-V-gQ?t=1165) [that this was a circle um so it's it's](https://youtu.be/3G8hsV-V-gQ?t=1169) [not perfect let's look at the other use](https://youtu.be/3G8hsV-V-gQ?t=1171) [case these two use cases about creating](https://youtu.be/3G8hsV-V-gQ?t=1174) [EXC colid draw shapes is more of an](https://youtu.be/3G8hsV-V-gQ?t=1177) [experiment from my side they are really](https://youtu.be/3G8hsV-V-gQ?t=1179) [not that good at the moment but let's](https://youtu.be/3G8hsV-V-gQ?t=1182) [create a smiley and let's see if the](https://youtu.be/3G8hsV-V-gQ?t=1184) [smiley is](https://youtu.be/3G8hsV-V-gQ?t=1186) [created there's our Smiley if I](https://youtu.be/3G8hsV-V-gQ?t=1189) [can get the smiley out of there so the](https://youtu.be/3G8hsV-V-gQ?t=1193) [smiley is actually pretty nice I think](https://youtu.be/3G8hsV-V-gQ?t=1196) [that's a I'm I'm happy with the smiley](https://youtu.be/3G8hsV-V-gQ?t=1199) [part the they can also try others I was](https://youtu.be/3G8hsV-V-gQ?t=1202) [successful with generating a car and a](https://youtu.be/3G8hsV-V-gQ?t=1206) [table and small things like that but](https://youtu.be/3G8hsV-V-gQ?t=1209) [again sometimes what's generated you](https://youtu.be/3G8hsV-V-gQ?t=1211) [need to remove background colors or make](https://youtu.be/3G8hsV-V-gQ?t=1214) [Parts transparent because it's hidden it](https://youtu.be/3G8hsV-V-gQ?t=1218) [takes a bit of experimentation to work](https://youtu.be/3G8hsV-V-gQ?t=1220) [it out but back to a look at the use](https://youtu.be/3G8hsV-V-gQ?t=1223) [cases so web development and play the](https://youtu.be/3G8hsV-V-gQ?t=1227) [other is generating EXC colit Elements](https://youtu.be/3G8hsV-V-gQ?t=1230) [which is super](https://youtu.be/3G8hsV-V-gQ?t=1233) [experimental creating and editing images](https://youtu.be/3G8hsV-V-gQ?t=1236) [we looked at a whole bunch of examples](https://youtu.be/3G8hsV-V-gQ?t=1239) [here um there are also additional use](https://youtu.be/3G8hsV-V-gQ?t=1241) [cases where you can just simply generate](https://youtu.be/3G8hsV-V-gQ?t=1245) [an image from a prompt you can also use](https://youtu.be/3G8hsV-V-gQ?t=1249) [this for visual brainstorming maybe we](https://youtu.be/3G8hsV-V-gQ?t=1253) [can look at this example as well so back](https://youtu.be/3G8hsV-V-gQ?t=1256) [to the brick road approach the visual](https://youtu.be/3G8hsV-V-gQ?t=1258) [brainstorming is about creating an image](https://youtu.be/3G8hsV-V-gQ?t=1262) [so I'm going to now choose visual](https://youtu.be/3G8hsV-V-gQ?t=1265) [brainstorm I'm just going to send this](https://youtu.be/3G8hsV-V-gQ?t=1268) [image over and I'm going to click run so](https://youtu.be/3G8hsV-V-gQ?t=1271) [the visual](https://youtu.be/3G8hsV-V-gQ?t=1274) [brainstorm creates a](https://youtu.be/3G8hsV-V-gQ?t=1276) [picture that somehow resonates with the](https://youtu.be/3G8hsV-V-gQ?t=1278) [content of the Whiteboard that you've](https://youtu.be/3G8hsV-V-gQ?t=1283) [created my idea is that looking look at](https://youtu.be/3G8hsV-V-gQ?t=1285) [the picture and looking at the](https://youtu.be/3G8hsV-V-gQ?t=1288) [Whiteboard it can spark some additional](https://youtu.be/3G8hsV-V-gQ?t=1290) [ideas so this is the image that was](https://youtu.be/3G8hsV-V-gQ?t=1293) [generated so this is about sketch noting](https://youtu.be/3G8hsV-V-gQ?t=1297) [for sure we have the sketch note artist](https://youtu.be/3G8hsV-V-gQ?t=1300) [we have this idea up here we have a bit](https://youtu.be/3G8hsV-V-gQ?t=1302) [of a diagram up in this corner it's](https://youtu.be/3G8hsV-V-gQ?t=1305) [actually this Leaf of ideas that are](https://youtu.be/3G8hsV-V-gQ?t=1308) [spreading all over it's it is a nice](https://youtu.be/3G8hsV-V-gQ?t=1313) [illustration is it helping me thinking](https://youtu.be/3G8hsV-V-gQ?t=1317) [about sketch noting well maybe it does](https://youtu.be/3G8hsV-V-gQ?t=1319) [so I can reflect on this image and](https://youtu.be/3G8hsV-V-gQ?t=1322) [connect it with the ideas from The Brick](https://youtu.be/3G8hsV-V-gQ?t=1326) [Road approach to skep thing and just see](https://youtu.be/3G8hsV-V-gQ?t=1328) [some links I'm actually going to save](https://youtu.be/3G8hsV-V-gQ?t=1332) [this image so again final reminder that](https://youtu.be/3G8hsV-V-gQ?t=1335) [you need to save the image locally if](https://youtu.be/3G8hsV-V-gQ?t=1338) [you want to keep it otherwise you come](https://youtu.be/3G8hsV-V-gQ?t=1342) [back tomorrow and this image is no](https://youtu.be/3G8hsV-V-gQ?t=1344) [longer going to be](https://youtu.be/3G8hsV-V-gQ?t=1347) [available I think we've looked at all](https://youtu.be/3G8hsV-V-gQ?t=1348) [the use cases so the other use case](https://youtu.be/3G8hsV-V-gQ?t=1351) [apart from illustrations is to generate](https://youtu.be/3G8hsV-V-gQ?t=1354) [new ideas and generate new ideas could](https://youtu.be/3G8hsV-V-gQ?t=1356) [be illustration of a quote it could be a](https://youtu.be/3G8hsV-V-gQ?t=1360) [visual brainstorm or a mermaid graph](https://youtu.be/3G8hsV-V-gQ?t=1362) [that illustrates an](https://youtu.be/3G8hsV-V-gQ?t=1367) [idea so then let's look at what's under](https://youtu.be/3G8hsV-V-gQ?t=1369) [the hood I'm going to be very quick on](https://youtu.be/3G8hsV-V-gQ?t=1372) [this but I think this is helpful and you](https://youtu.be/3G8hsV-V-gQ?t=1375) [also saw how I'm using this in the](https://youtu.be/3G8hsV-V-gQ?t=1377) [presentation so you need to select the](https://youtu.be/3G8hsV-V-gQ?t=1381) [elements you want to include in your](https://youtu.be/3G8hsV-V-gQ?t=1384) [prompt on the canvas so for example like](https://youtu.be/3G8hsV-V-gQ?t=1387) [this I can select these elements and](https://youtu.be/3G8hsV-V-gQ?t=1391) [then these are going to be the ones that](https://youtu.be/3G8hsV-V-gQ?t=1394) [I'm sending to open](https://youtu.be/3G8hsV-V-gQ?t=1396) [AI for some of the prompts like for](https://youtu.be/3G8hsV-V-gQ?t=1399) [example for the quote you don't need to](https://youtu.be/3G8hsV-V-gQ?t=1402) [select elements because then you're only](https://youtu.be/3G8hsV-V-gQ?t=1405) [sending the text prompt and that's](https://youtu.be/3G8hsV-V-gQ?t=1408) [okay then you choose the task now when](https://youtu.be/3G8hsV-V-gQ?t=1412) [you choose the task then depending on](https://youtu.be/3G8hsV-V-gQ?t=1416) [the type of task you saw that in case of](https://youtu.be/3G8hsV-V-gQ?t=1418) [selecting the image edit then the](https://youtu.be/3G8hsV-V-gQ?t=1423) [picture and the excolo elements were](https://youtu.be/3G8hsV-V-gQ?t=1428) [taken in two separate parts so you](https://youtu.be/3G8hsV-V-gQ?t=1431) [remember here that we were looking at](https://youtu.be/3G8hsV-V-gQ?t=1434) [this mask like that and here if I start](https://youtu.be/3G8hsV-V-gQ?t=1439) [excal](https://youtu.be/3G8hsV-V-gQ?t=1443) [AI you can see that in the normal case](https://youtu.be/3G8hsV-V-gQ?t=1444) [this entire image would be sent to open](https://youtu.be/3G8hsV-V-gQ?t=1448) [AI if I choose here edit image then this](https://youtu.be/3G8hsV-V-gQ?t=1451) [is split into two I have the](https://youtu.be/3G8hsV-V-gQ?t=1455) [picture and I have the mask and wherever](https://youtu.be/3G8hsV-V-gQ?t=1459) [the mask is black that's where the image](https://youtu.be/3G8hsV-V-gQ?t=1464) [is going to be generated maybe this can](https://youtu.be/3G8hsV-V-gQ?t=1466) [be much more visible if I do it here let](https://youtu.be/3G8hsV-V-gQ?t=1469) [me bring this to the](https://youtu.be/3G8hsV-V-gQ?t=1473) [front like this and so for example if I](https://youtu.be/3G8hsV-V-gQ?t=1476) [would want to change this house into a](https://youtu.be/3G8hsV-V-gQ?t=1480) [skyscraper and then I would send I would](https://youtu.be/3G8hsV-V-gQ?t=1486) [open exol AI like this and then you can](https://youtu.be/3G8hsV-V-gQ?t=1490) [see here that this is where the](https://youtu.be/3G8hsV-V-gQ?t=1494) [skyscraper will go you can see the mask](https://youtu.be/3G8hsV-V-gQ?t=1497) [and you can see the](https://youtu.be/3G8hsV-V-gQ?t=1500) [image so depending on the task you will](https://youtu.be/3G8hsV-V-gQ?t=1503) [see a different preview image either the](https://youtu.be/3G8hsV-V-gQ?t=1506) [image plus the mask or the image only](https://youtu.be/3G8hsV-V-gQ?t=1509) [you can then provide your text prompt](https://youtu.be/3G8hsV-V-gQ?t=1513) [and optionally modify the system prompt](https://youtu.be/3G8hsV-V-gQ?t=1516) [so the system prompt is this one up here](https://youtu.be/3G8hsV-V-gQ?t=1519) [in case of edit image there is actually](https://youtu.be/3G8hsV-V-gQ?t=1523) [no system prompt but most of the cases](https://youtu.be/3G8hsV-V-gQ?t=1525) [there are so this is the customize](https://youtu.be/3G8hsV-V-gQ?t=1528) [system prompt part and then when you hit](https://youtu.be/3G8hsV-V-gQ?t=1531) [run at the bottom then depending on the](https://youtu.be/3G8hsV-V-gQ?t=1534) [activity you selected different things](https://youtu.be/3G8hsV-V-gQ?t=1538) [will happen either a mermaid graph is](https://youtu.be/3G8hsV-V-gQ?t=1540) [generated or an EXC colro drawing is](https://youtu.be/3G8hsV-V-gQ?t=1544) [generated or a web app or maybe dolly is](https://youtu.be/3G8hsV-V-gQ?t=1547) [executed and an image is created in some](https://youtu.be/3G8hsV-V-gQ?t=1551) [cases and this is the case then you](https://youtu.be/3G8hsV-V-gQ?t=1554) [create an an image prompt and you want](https://youtu.be/3G8hsV-V-gQ?t=1558) [you add an image and a prompt and you](https://youtu.be/3G8hsV-V-gQ?t=1562) [want to create a new image based on that](https://youtu.be/3G8hsV-V-gQ?t=1564) [inspired by that like my little house so](https://youtu.be/3G8hsV-V-gQ?t=1567) [this was uh these are all the examples](https://youtu.be/3G8hsV-V-gQ?t=1570) [of that then what happens is first I](https://youtu.be/3G8hsV-V-gQ?t=1574) [call GPT vision and GPT Vision generates](https://youtu.be/3G8hsV-V-gQ?t=1577) [an image prompt and then with that I go](https://youtu.be/3G8hsV-V-gQ?t=1581) [to Dolly and I generate the image and](https://youtu.be/3G8hsV-V-gQ?t=1585) [finally if you like the image you should](https://youtu.be/3G8hsV-V-gQ?t=1589) [save it locally right click save locally](https://youtu.be/3G8hsV-V-gQ?t=1593) [or if not then open II will delete the](https://youtu.be/3G8hsV-V-gQ?t=1596) [image in 30](https://youtu.be/3G8hsV-V-gQ?t=1600) [minutes I'm not saving the images](https://youtu.be/3G8hsV-V-gQ?t=1602) [automatically to the Vault because I'm](https://youtu.be/3G8hsV-V-gQ?t=1605) [assuming that there's going to be lots](https://youtu.be/3G8hsV-V-gQ?t=1608) [of rubbish generated by open Ai and you](https://youtu.be/3G8hsV-V-gQ?t=1609) [don't want to clutter your Vault so this](https://youtu.be/3G8hsV-V-gQ?t=1612) [requires a bit of deliberate action on](https://youtu.be/3G8hsV-V-gQ?t=1615) [your side to save what you find to save](https://youtu.be/3G8hsV-V-gQ?t=1618) [it locally and finally let's look at](https://youtu.be/3G8hsV-V-gQ?t=1622) [what it takes to get started with this](https://youtu.be/3G8hsV-V-gQ?t=1625) [so first of all you need to install xol](https://youtu.be/3G8hsV-V-gQ?t=1628) [AI from the script Library how does it](https://youtu.be/3G8hsV-V-gQ?t=1631) [work you click here to open the obsidian](https://youtu.be/3G8hsV-V-gQ?t=1633) [tools panel and top left you see install](https://youtu.be/3G8hsV-V-gQ?t=1636) [or update excal draw scripts if I open](https://youtu.be/3G8hsV-V-gQ?t=1640) [this then I can search for exol](https://youtu.be/3G8hsV-V-gQ?t=1644) [AI like this it will take me here and if](https://youtu.be/3G8hsV-V-gQ?t=1648) [I click on this then here I can just](https://youtu.be/3G8hsV-V-gQ?t=1652) [simply click install now it's already](https://youtu.be/3G8hsV-V-gQ?t=1654) [installed so I didn't I don't need to](https://youtu.be/3G8hsV-V-gQ?t=1658) [install it but this is how I would](https://youtu.be/3G8hsV-V-gQ?t=1660) [install it if I click this it will say](https://youtu.be/3G8hsV-V-gQ?t=1662) [installed xol AI once you have exol ai](https://youtu.be/3G8hsV-V-gQ?t=1665) [working you need to go to open Ai and](https://youtu.be/3G8hsV-V-gQ?t=1669) [you need to create an account and add](https://youtu.be/3G8hsV-V-gQ?t=1672) [money to that account so this is the](https://youtu.be/3G8hsV-V-gQ?t=1674) [link you need to open and you can see](https://youtu.be/3G8hsV-V-gQ?t=1676) [here that this is my balance I have](https://youtu.be/3G8hsV-V-gQ?t=1680) [$392 by the way generating images we can](https://youtu.be/3G8hsV-V-gQ?t=1684) [look at how much today's usage cost so](https://youtu.be/3G8hsV-V-gQ?t=1687) [generating all the images we did right](https://youtu.be/3G8hsV-V-gQ?t=1691) [now I was already I think at 9 cents so](https://youtu.be/3G8hsV-V-gQ?t=1694) [today this image generation for the](https://youtu.be/3G8hsV-V-gQ?t=1697) [video cost me about 40 cents I don't](https://youtu.be/3G8hsV-V-gQ?t=1699) [think it's a huge amount of money so](https://youtu.be/3G8hsV-V-gQ?t=1704) [this is there you can see](https://youtu.be/3G8hsV-V-gQ?t=1706) [the usage information as well once you](https://youtu.be/3G8hsV-V-gQ?t=1708) [have your account and you've added money](https://youtu.be/3G8hsV-V-gQ?t=1711) [to the account you need to add at](https://youtu.be/3G8hsV-V-gQ?t=1714) [minimum $5 otherwise the GPT Vision](https://youtu.be/3G8hsV-V-gQ?t=1716) [model is not going to be available to](https://youtu.be/3G8hsV-V-gQ?t=1720) [you if you have at least $5 or on your](https://youtu.be/3G8hsV-V-gQ?t=1722) [account you still need to wait about 10](https://youtu.be/3G8hsV-V-gQ?t=1725) [20 minutes for open AI to activate your](https://youtu.be/3G8hsV-V-gQ?t=1728) [access and then you can come here and](https://youtu.be/3G8hsV-V-gQ?t=1731) [configure in obsidian you need to create](https://youtu.be/3G8hsV-V-gQ?t=1734) [an open AI API key you can see the link](https://youtu.be/3G8hsV-V-gQ?t=1738) [right here if I click on this it takes](https://youtu.be/3G8hsV-V-gQ?t=1741) [me to the API keys I can click here to](https://youtu.be/3G8hsV-V-gQ?t=1743) [create a new secret key and then the key](https://youtu.be/3G8hsV-V-gQ?t=1746) [is going to be created and then I need](https://youtu.be/3G8hsV-V-gQ?t=1750) [to go to plug-in settings right here and](https://youtu.be/3G8hsV-V-gQ?t=1753) [I need to click on EXC colar draw AI](https://youtu.be/3G8hsV-V-gQ?t=1756) [settings and here I can](https://youtu.be/3G8hsV-V-gQ?t=1759) [configure my API key and my different](https://youtu.be/3G8hsV-V-gQ?t=1762) [models as well and finally when you're](https://youtu.be/3G8hsV-V-gQ?t=1767) [done come here to the tools panel and](https://youtu.be/3G8hsV-V-gQ?t=1770) [find exol AI](https://youtu.be/3G8hsV-V-gQ?t=1775) [here amongst the downloaded scripts if](https://youtu.be/3G8hsV-V-gQ?t=1778) [you long click on it then you can add it](https://youtu.be/3G8hsV-V-gQ?t=1781) [pin it to the side panel and from then](https://youtu.be/3G8hsV-V-gQ?t=1783) [on it's going to work as I've](https://youtu.be/3G8hsV-V-gQ?t=1786) [demonstrated it to you uh in the](https://youtu.be/3G8hsV-V-gQ?t=1788) [video so that's all I wanted to share](https://youtu.be/3G8hsV-V-gQ?t=1791) [with you today I already used it a lot](https://youtu.be/3G8hsV-V-gQ?t=1794) [in my workflows I enjoy it so much yes](https://youtu.be/3G8hsV-V-gQ?t=1798) [it costs a little money but the amount](https://youtu.be/3G8hsV-V-gQ?t=1802) [is not so much and I think the benefit](https://youtu.be/3G8hsV-V-gQ?t=1804) [you're getting with the images with the](https://youtu.be/3G8hsV-V-gQ?t=1808) [mind maps with the workflows is super](https://youtu.be/3G8hsV-V-gQ?t=1810) [valuable give it a try and let me know](https://youtu.be/3G8hsV-V-gQ?t=1813) [what you think in the comments below](https://youtu.be/3G8hsV-V-gQ?t=1815) [thank you](https://youtu.be/3G8hsV-V-gQ?t=1818)