I was recently fortunate enough to pick up a small and interesting piece by her and I wanted to make sure to share what I knew about her online. ![]() There is very little information available online about the California artist Margo Alexander, and that is a shame. ![]() I hope that Meta opens it up to the public soon. I also think it could be useful for brainstorming visual ideas about characters, concepts, and even fiction. I think it would be particularly good at creating trippy art for album covers or single artwork on music streaming sites. I think, even in this early state, it has some real possibility for generating art in some situations. Overall, I think Make-a-Scene is interesting and fun. The first image it generated looks almost like usable clip art. I drew a picture of a person-shaped blob holding a spoon-shaped blob, and gave it the prompt "a woman eating breakfast". I though about the type of images that marketers might need. Interestingly, it didn't necessarily understand who the fictional characters were, but it knew that they were soldiers.įor my last experiment, I went back to something more generic. I included lightsabers in sections of the image labeled as "person" so Make-a-Scene added some funky looking arms onto the people. You can see how my drawing led the AI astray in the generated images. As you can see from the generated images, it struggled much more to understand both my poor drawing, and the very specific text prompt. Next, I fed it the much more specific prompt of "Emperor Palpatine training Anakin Skywalker". I particularly liked the first two images.Īs you can see, Make-a-Scene tries to follow the image input as closely as possible, and it's able to interpret the phrase "impressionist painting" in many different ways. This image shows the input along with four generated images. Then I gave it the prompt "an impressionist painting of california". I drew an image with a sky, a mountain, a river, and a fence. In this post, I'm going to show you my first experiments with Make-a-Scene, and you can see how it compares to the other image generation tools.Īs a lover of California landscapes, and a collector of the painters known as the California Impressionists, I had to start by trying to generate some California landscapes. Make-a-Scene isn't yet open to the public, but as a Meta employee, I was able to get my hands on it early. A person can sketch out a rough scene as input, then use text to tell Make-a-Scene how to fill it in. It's a more collaborative tool than some of the other image generators made by other companies. Their new tool is called Make-a-Scene and it takes both an image and a line of text as prompts. Last week Meta announced their entry into the field of artifical intelligence image generation. Here are my first images created using this method and the given prompt. To change the prompt, simply alter the string that is fed into 'model.text_to_image' on line 8. ![]() Images = model.text_to_image("california impressionist landscape showing distant mountains", batch_size=1) Model = keras_cv.models.StableDiffusion(img_width=512, img_height=512) Save the following code into a file called whatever you want. Pip install keras-cv tensorflow tensorflow_datasets matplotlib Use the following command to install all needed dependencies. I had to manually install a few dependencies. Name "LongPathsEnabled" -Value 1 -PropertyType DWORD -Force New-ItemProperty -Path "HKLM:\SYSTEM\CurrentControlSet\Control\FileSystem" ` ![]() I think the easiest is to run PowerShell as administrator, then run the following command: You can install pip by downloading the installation script at. Otherwise, type 'python' again to trigger the Windows Store installation process. If you already have python, then you can skip this step. First, check if python is installed using the following command: We only need to make a few modifications to that tutorial to get everything to work on Windows. I started with that tutorial because it is relatively system agnostic, and because it uses optimizations that will help on my low powered Windows machine. This tutorial is based on the stable diffusion tutorial from keras.io. How to set up stable diffusion on Windows In this post, I'm going to show you how you can generate images using the stable diffusion model on a Windows computer.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |