AI Wrote the Script and Made this Architectural Animation!

Hello dear friends. In this video I'll show you how to create impressive animation films starting from any visualized image of an architectural project and what technologies we currently have available. I'll try to explain these to you. Of course I'll try to explain both the manual part and the part we can do automatically. Dear friends, for the manual part I'm currently using Kling AI because Kling AI is a high resolution video production tool. Especially recently it was updated with a 4k resolution image generation feature. Therefore starting from a 4k image or even a 2k image we can produce very high quality and very realistic animations. There's a very nice feature here in Kling AI 3.0. For example I'm importing one of the images we used most recently right here. This is currently a 4k image as you can see. Now in Kling 3.0 we have a section specifically called multi shots or custom multi shots. So first I'm selecting 4k for the image here. After specifying how many seconds it will be, let's say our image is 15 seconds long and here you can write in detail what will happen every few seconds. For instance you can write things like let this happen in the first four seconds or let that happen in the first five. For this of course what am I going to do? I'm going to use ChatGPT. Friends, I mean I'll benefit from ChatGPT when it comes to writing the script. Now I'm bringing my image and dropping it here. I'm saying look I'm going to make an animation film by carefully creating shots from many different and various angles of this image. I have 15 seconds for an animation that's impressive and can present the character of this project for every four seconds, every four seconds and so on. Write a script. Create the scripts and scenes you've written as individual prompts. I'm going to use these. Let's say I'll use them in Kling AI as well. For example Kling AI. You can also write it like this. It doesn't matter. It understands the point anyway. Now the system is analyzing your image. It says for you and so on the usual things ChatGPT says. This says scene one. The first scene it says the wow effect. For example I'm copying this prompt right here and I'm coming over. I'm pasting this here for the first four second scene. Let's see how many shots it will make in total. What does this say? It says two seconds. Okay let's do it that way. Let's have the first two seconds be like this. Two seconds is a bit short for architectural visuals but that's okay. Then it says between three and seven seconds. This says between 3.5 and seven seconds. The feeling of human life. So how many seconds will this be? Let's say we have this. Let's not call it two seconds. Let's call it three friends because this is very short. Then let this be four seconds. That's seven seconds in total and from here we come back to this. Between 7 and 11 seconds we have a prompt like this. Let's call this four seconds as well friends. It's already 8, 9, 10, 11. Then we also have our final shot between 11 and 15 seconds. Bring this and place it back here again. So we've written a scenario. We've set the duration here. We want a 4k visual and it'll use 750 credits for this and the system has started working now. Now this is nice. It's good but I'm tired of doing this manually now guys. I thought let me automate this process. There are other similar AI model tools as well. Of course I mean it's not just Cling AI. Various models will emerge. Maybe we can use those too. How should we do it? Like that. This time we added a module called Apricot from Archifruits AI. The Apricot module everyone. When you bring and drop the same visual here you don't need to do anything else. We just click create film. The system reads this visual in the background. It prepares a special scenario for your visual. It actually automates what I did manually over there. The system generates the prompts using Cling AI in the background. What we're showing here right now. The animation we're about to create by the way. We've selected two. The system will automatically create the same thing here in an automated way without any input. Now we'll see the difference between the two. Dear friends now we're watching our video created in Cling AI. Now look the sunset is beautiful. The background sound turned out great. It really is perfect. There's some talking and stuff like that. Of course as you can see. Yes this is nonsense because we don't have a project like this. I mean it needs to provide something from these angles. Likewise another different film. A film with the same prompt again. It is so nice to be outside. The weather is perfect. Look it looks very nice. For example these parts can be used. Then this. It's okay I guess. So what have we done? What kind of result did Archifruits AI give? Let's take a look at that too. Look at the It's really nice. There's no background noise. It's mostly music. Ready. And like this. As you can see it felt much more cinematic to me right now honestly. Because the AI created it itself. It created the other one too. It varies by the prompt but it's essentially the same process. So what did we achieve? Actually we've automated what we were doing manually here guys. Of course this automation comes with a cost. You can use it this way. We can make films for multiple visuals and then combine them all into one film. We have the chance to create some quite nice animations. This isn't a very long process. It's completed in two to three minutes. So you can make films like this starting from a single visual. You can work manually through Kling AI if you want. Or you can do it directly through Archifruits AI without any hassle.