Awesome Generative

It takes good technology and clever prompt engineering to produce quality generative AI content. Director Simon Valentine, writer Erlend Loe, artist Edmond Yang, and editor Alex Holm used AI tech to make this short film about a death row inmate’s unexpected final wish. They created the entire stop-motion style film in less than 48 hours. (Thanks, Rob!)

Nervous System makes mathematically-generated accessories, jewelry, and puzzles. These unique jigsaw puzzles resemble the geometry of bismuth crystal formations. Each puzzle has a one-of-a-kind artwork is made from laser-cut maple plywood with digitally printed images. The finished puzzles measure about 11″ across and average 267 matrix-cut pieces.

Some may dismiss the use of generative AI for creating art, but in the hands of the right person, it can be used to create things none of us imagined possible. Filmmaker James Gerde used AI tech to help create animations that imagine humans if they were made of noodles. Each clip is based on footage of talented dancers, and Gerde made them into pasta.

OpenAI’s new ChatGPT language model GPT-4o can respond to and with text, audio, images, and video. But perhaps more scarily amazing is that in Voice Mode – which allows it to respond using an AI-generated voice – it’s as snappy and natural-sounding as a human. GPT-4o is available even to free users, but using it in Voice Mode is limited to paid subscribers.

Abandoned Films is back with another trippy, AI-generated movie trailer. This time, they took the 1997 sci-fi classic The Fifth Element and applied a 1950’s big-screen aesthetic to Leeloo, Corbin Dallas, Vito Cornelius, Ruby Rhod, Zorg, and their retro-futuristic world. Will our heroes find the stones and save us before the Ultimate Evil swallows the universe?

Abandoned Films imagines what a Super Mario Bros. movie might have looked like as a movie shot in Super Panavision 70 back in the 1950s. The surreal take on Nintendo’s iconic plumbers is made extra trippy courtesy of generative AI tech. The images are by Midjourney, video by Runway, voices by ElevenLabs, and the script by ChatGPT.

This impressive yet creepy AI tech can take a single still image and make it appear to speak or sing any audio. Developed by researchers from Alibaba’s Institute for Intelligent Computing, EMO: Emote Portrait Alive’s model was trained on more than 150 million images to work its magic. The video is peppered with examples of the convincing deepfakery.

And the court will rise, while the pillars all fall. Peter Gabriel has been creating musical masterpieces since the 1960s. The Court comes from his new album i/o. The track explores society’s need for order and the flaws of judicial systems. The video was created by Junie Lau using various AI tech, including Stable Diffusion, ChatGPT, MidJourney, and DALL·E 2.

FRVR’s AI game development platform will let users create their own video games using text prompts. The demo shows it taking a description of a top-down shooter and generating the code for a playable game. As the user refines their prompts, the game gets better. Users will be able to publish and monetize the games they create too. Full walkthrough video here.

A typical flipbook animation displays its images at roughly 12 frames per second. Andymation wanted to know if he could smooth out the steps in his flipbooks by filling extra frames with AI interpolation software. Will the additional frames improve the look of his animations or make them just look incredibly weird?

We’ve seen what artificial intelligence can do when asked to make a pizza commercial; now AI has been turned loose on a beer spot. Private Island used Stable Diffusion, Runway, and Modelscope to generate their version of those summertime commercials with bros ogling women while they sip their bland light beer.

French filmmaker Remi Molettee is known for their wildly inventive generative digital art. In the AI-enabled short film, Symbiosis, Remi transformed dancers the Ebinum Brothers into living, moving tree roots. As their bodies move and intertwine, they appear as wooden surrogates for blood vessels and veins.

Machine learning tech has enabled some truly imaginative imagery. Artist Vadim Epstein helped create a set of ML text-to-video tools that generated this landscape of pseudo-realistic organic forms incorporating veins, bones, and plants. Best enjoyed in full screen with headphones on. Soundtrack by Dvar.

AI image generation technology continues to improve – though it’s still not great at dealing with things like text and logos. While the results of ThomasDotCodes’ breakfast cereal experiment are questionable, we enjoyed watching the weird stuff styleGAN2 came up with when trained with 700 images of cereal boxes.

This experimental animated film takes us deep into a web of humans and technology. The surreal effect was created by artist ThomasDotCodes with the help of VQGAN-CLIP – a natural language image generation toolkit. Watch in 1080p or higher in full-screen mode for maximum impact. Then, go deeper into the Matrix.

Tools like DALL·E 2 have proven it’s possible for AI tech to create art based on text. Neural Synesthesia fed text descriptions of the history of the Earth and the evolution of its species into StableDiffusion, which it used as a guide to creating the video Voyage Through Time. The music is Order from Chaos by Max Cooper.