In December 2022, there was an explosion of AI-based products. Many leaders and futurists predict that Ai will become the main driver of 2023.
Our Sommo team also dived into this rabbit hole. We have created the Dyvo application, which allows you to create art drawings and avatars from your photos using AI. Users can generate profile pictures, pet portraits, dating photos, and content for Twitter / TikTok / Facebook / Instagram.
With our no-code approach, the time from the idea to the first release took less than a month, but let’s start from the beginning.
Harold Cohen developed one of the first significant AI art systems in the 1960s at the University of California. On 22 August 2022, the release of Stable Diffusion made the technology more accessible and free to use, enabling a surge in further applications to generate realistic images conditioned on text descriptions, image-to-image translations guided by a text prompt, and out- or inpainting within an image.
So, in November 2022, we challenged ourselves to create an AI-based product, exciting and accessible to millions of users.
We tested different implementations of Stable Diffusion technology, researched the experience, queries, and interests of users, and chose, in our opinion, the most exciting direction.
Modern people spend an unprecedented amount of time online, and form their image online. Our idea was to help them do this, literally - create a lot of high-end photos that will be used as user avatars in various placements - from professional hyper-realistic profiles on Linkedin to fantasy cyberpunk portraits for computer games.
The challenge of applying Stable diffusion in this case was
(a) to create images similar to the people depicted in the original photos,
(b) avoid artifacts and other bugs associated with AI,
(c) generate images that users will like (the most significant challenge).
To solve this problem, we conducted experiments with training models, prompts, and configs (sampling methods, steps, CFG scale, X/Y plotting, and seeds).
If you are interested in going deeper into the process of using and configuring Stable Diffusion, there are a lot of headers in the network, for example:
Github Repository with the guides
Stable Diffusion: Tutorials, Resources, and Tools
Stable Diffusion Guide by CDcruz
If you have ever created your product, you know that one of the challenges is naming.
Since the end of November was filled with the Christmas mood, we named the application "Dyvo", which means "Miracle" in Ukrainian.
We created Dyvo for any online character, literally - a person, a couple, or even a cat or a dog. So the design is bold, super easy, fancy, vivid, and colorful.
Sommo is a dedicated low-code/no-code team, so we have extensive experience with different no-code platforms. For Dyvo, we chose Bubble.io, one of our favorite no-code tools, because of its flexibility and ability to quickly integrate various 3-party software - from complex and unique AI tools to popular payment and analytical services.
Dyvo’s second development secret is to use its own no-code development tool Natively to convert the Bubble application to mobile iOS/Android. For Dyvo, having a presence on the App Store and Google Play Market was an important way of user acquisition.
Creating mobile applications with Natively took no more than an hour. In addition, we could customize important native features - social auth, in-app purchases, push notifications, camera, etc.
When opening Dyvo for the first time, the user can check the quality of the created AI pictures before signing up. You can compare the original photos and hundreds of images generated by Dyvo for these users. It is handy (see the result in advance) and fun!
You can also learn how Dyvo works and browse hundreds of photos generated and published by Dyvo users (community).
After signing up, users can see (or skip) Onboarding with the main steps to create Dyvo avatars.
By clicking the “Create avatar” button, the users initiate generating flow: checking out, picking appearance, and uploading their photos.
Sticking to the recommendations when selecting photos is essential to create great avatars. Users should upload selfies with different facial expressions, backgrounds, clothes, angles, lighting, and bigger than 512 x 512 px.
We don’t recommend using the same background/shot, the same emotion, selfies with sunglasses, too much makeup, bikini/swimsuits, or nudes.
After uploading photos, the magic starts - the app spins up a machine-learning model individualized just for you. You will get your avatars in 50+ styles in less than an hour. Note that some could be flawed. AI algorithms may generate weird artifacts, inaccuracies, and defects in output images. It’s expected, and the resulting images will never be 100% perfect.
In addition to generating static pictures, you can:
animate your avatar;
extend it from a small square image to a 4k 2:3 professional photograph;
make your avatar talk - select the avatar, write your text, and we'll voice your avatar talk with AI video like a real character.
The privacy of Dyvo users is essential: all your uploaded photos are deleted automatically within one week after the avatar finishes processing.
Within the first month, Dyvo grew by 100k users (android, iOS, and web), and generated thousands of avatars for them. Try creating avatars for yourself or your friend/pet - this is an awe-inspiring experience.
Our short-term plans are UI/UX and AI model improvement, more dedicated styles, and localization.
But the rabbit hole was so deep that we are constantly looking for new AI applications to make the future more harmonious and secure. If you have any ideas, write us, and let’s implement them together.
P.S. This article is written using AI ;)