Wunjo

Hey everyone! As we approach the end of this year, I’ve been reflecting on everything we’ve accomplished and where we can go next. I've created this video as a small teaser, what you will able to do with one click in Wunjo in future — watch the car drive on water with the intriguing message: «What is Next?» 

Stop the train, I need to get off! It feels like we’re moving too fast: not even a month has passed since the November update, and here comes the December one! The demo version is already updated. Notice the fresh, more polished interface? All secrets will be revealed in just a week.

This might sound like great news—I've just compiled the first build of the update! In my next post, I'll share an exclusive pre-release version available only to Boosty subscribers after alpha tests. 

Here’s the full list of improvements, beyond what I’ve previewed before:

It’s no secret that most AI-driven applications require CUDA to fully unleash their potential, which means Nvidia GPUs are usually a must. Whether it’s Wunjo or countless other AI generation services, they all rely on Nvidia under the hood.

But something exciting happened yesterday—Wunjo successfully ran on an AMD GPU! You can find detailed instructions on how to make it work in Issue 65, with a follow-up in Issue 68 or updated README. In short, you’ll need to install ZLUDA, along with Torch and XForms from the RCom repo. Once set up, everything runs smoothly.

Now, for the downside: Nvidia has thrown a wrench in the works with a new license agreement for CUDA, effectively halting the progress of projects like ZLUDA. Even AMD has distanced itself from it.

So, what does this mean? Don't waste time! While ZLUDA is still functional, it’s the perfect opportunity to upgrade your AMD processor and install the software before it’s too late! Especially if you like to figure out the solution.

According to the recent poll on Telegram, the next update will bring back talk head from photos—but this time, it's improved. You'll be able to animate faces not only in photos but also in videos, and potentially even for animals and cartoon characters, not just people. Stay tuned, exciting things are coming!

It's time for a big overview of the new functionality with an explanation of the settings and parameters.

In this video, I'll explore how you can use Wunjo to change your skin color, ethnicity, or gender, all while maintaining complete control over the process. With just 8GB of video memory, you'll be able to achieve impressive results.

I will demonstrate how to work with voice cloning for dubbing videos, as well as how to generate videos and images effortlessly from text and images.

Hello everyone! Exciting news! Just as we were getting comfortable with update 2.0.2, update 2.0.3 has arrived! This latest release enhances the quality of video restyling, introduces controlled video restyling to meticulously track all nuances in Wunjo Pro, and adds image generation capabilities such as inpaint and outpaint with your custom SD 1.5 models. You can now generate videos from 24 FPS to 4 seconds or longer with lower FPS.

Video restyling and stylization in Wunjo Pro has become better and more convenient than ever!

The best part? The feature image and video generation is available not only in Wunjo Pro but also in the Community Edition!

And if you missed out on update 2.0.2, don't worry! Here's a video showcasing the functionality this update brought: