I recently came across a fan trailer for Grand Theft Auto VII, Egypt on YouTube, created by German music video director Yonatan Dor. His company, Dor Brothers, has developed deep expertise in generative AI using it in the production of over 200 music videos. One of the things I’ve been tracking for Forbes is the rapid development of cinematic AI, so of course I already knew about the Dor Brothers’ incredible AI-enhanced music video for the supergroup SiM, Hide and seek. With the release of their GTA trailer, I reached out to Instagram to get their story, just like I had to for the AI filmmakers. Caleb and Shelby Ward, Dave ClarkNicolas Neubert and Beautiful aunts. I wanted to know more about how he used AI to achieve this.
Dor frequently speaks at AI events and collaborates with teams at Microsoft and Pika Labs. “THE Hide and seek The project for SiM began when label UNFD contacted us to create a music video that captured SiM’s distinctive aesthetic. With only five days (!) of production, we quickly conceptualized a style blending traditional Japanese art with a modern, explosive twist to match SiM’s artistic identity. The label gave us a very minimal brief – “Devil/Demon, Bat, Resuscitation (Revival), Play Dead, Immortality” – that’s where our imagination took over. We visualized scenes such as demons playing guitars, massive speakers invading a city, and pre-apocalyptic alarms signaling “The end is near, SiM is here,” mirroring the band’s intense live performances.
In the softer sections of the song, we leaned toward traditional Japanese aesthetics, reimagining “The Great Wave off Kanagawa” to match the modern vibe of the video. The video ends with a poignant image: a man in a destroyed city touching an opening eye, symbolizing a return to pure, unadulterated art. To create this video, we generated a total of ~2,230 images. This figure does not take into account additional unused clips produced with Pika Labs (+300-500).
For the GTA VII – Egypt project, Dor leveraged Midjourney’s “Style Reference” feature to reimagine iconic video games with a unique twist. “The idea of setting a GTA game in Egypt sparked our imagination, combining Rockstar’s signature humor with a touch of originality,” he said. To bring this vision to life, Dor used:
1. Halfway through to create initial images using the style reference tool.
2. Pika Labs for animating these images.
3. Photoshop for image editing and cleaning.
4. ElevenLabs for AI-powered dramatic storytelling.
5. Adobe Premiere for video editing.
6. Wonderful AI for image scaling and sharpening.
There’s another brother Dor, who used to make music videos with Dor, but he’s doing something else now. “I hope he comes back one day,” he said. “But I feel like the animators I work with are brothers too.” Dor mentioned that he got into AI after discovering a YouTube video in 2022 that had only been viewed a few hundred times, when a very early version of Generative AI was introduced. This was before Midjourney or even Stable Diffusion existed. It was called VQGan for those who might be interested. “I was initially skeptical about its reality, but was amazed by its potential after trying it, despite producing a terrible first image. This experience convinced me of the potential of the tool and led me to devote 8 to 12 hours a day to mastering it.
“I first found clients by offering AI music videos on Fiverr. This was actually the first time that AI visuals were offered on the platform. Dor explained. “From there, I also created a few YouTube videos that got attention and shared my footage in public groups to build an initial audience. Now we attract clients from various sources for a wide range of projects.
Dor highlighted the dramatic changes we are seeing in generative AI tools, predicting that we will see a significantly different level of AI-generated content in the coming year. Yesterday, OpenAI unveiled a new generative AI tool called Sora. Sora is revolutionizing the AI video generation scene to an absolutely unprecedented level. So much has changed in the last few months, too much to summarize briefly. This technology is evolving at an incredible pace, with advancements almost doubling every month. If I were to produce our older videos today, I would have a much wider range of tools at my disposal. Today there are many tools allowing a fascinating mix of different techniques. AI threatens to disrupt media, social networks and our personal communications. What happens when we no longer know what is real? We will know soon.