Neill Blomkamp releases AI-generated short film Nightborne using ByteDance’s Seedance 2.0
Director Neill Blomkamp’s 13-minute sci-fi short, Nightborne, is produced by his AI startup Barley Studios and relies entirely on ByteDance’s Seedance 2.0 text-to-video generator for its visuals.
1 source · cross-referenced
- Neill Blomkamp premiered a 13-minute AI-generated sci-fi short, Nightborne, produced by his new AI startup Barley Studios.
- The film’s visuals were created entirely with ByteDance’s Seedance 2.0 text-to-video generator.
- Nightborne is loosely based on Peter Watts’ 2014 novel Echopraxia and set against a US–Syria military conflict.
- The short features characters modeled after human actors but exhibits common AI-generated video artifacts such as gibberish signage and unnatural dialogue emphasis.
Director Neill Blomkamp premiered a 13-minute sci-fi short titled Nightborne, produced by his newly formed AI startup, Barley Studios. The film is loosely based on Peter Watts’ 2014 novel Echopraxia and set against a military conflict between the United States and Syria.
Nightborne’s visuals were generated entirely using ByteDance’s Seedance 2.0 text-to-video model, according to Blomkamp’s announcement and reporting. Blomkamp described the short as a “test start” intended to demonstrate the capabilities of generative AI in filmmaking, with ambitions to eventually produce a full feature using the same approach.
The short features characters whose voices and faces are modeled after human actors, and Blomkamp stated that 32 human actors agreed to have their likenesses used on-screen. Blomkamp also said that real concept artists contributed to the project, and Austyn Daines handled editing. Despite this human involvement, critics highlight persistent AI artifacts in the final product, including background signage written in gibberish and dialogue delivered with unnatural emphases.
Reviewing Nightborne for The Verge, Charles Pulliam-Moore argues that the film’s polished presentation cannot overcome its fundamental limitations as an AI-generated work. He notes that the short relies on rapid cuts between short clips to obscure Seedance 2.0’s inability to generate longer coherent sequences, and that Blomkamp’s creative voice is barely perceptible in the final product.
Pulliam-Moore further contends that Nightborne exemplifies common issues with current text-to-video models, such as a lack of understanding of subtle human performance details and reliance on training data rather than original creative intent. He concludes that, aside from its use of generative AI, the short offers little that is artistically distinctive.
- Aug 25, 2026 · Google AI — Blog
Google Search adds AI-powered home decor visualization and shopping tools
Trust79 - Aug 25, 2026 · MIT Technology Review — AI
Humanoid robots take center stage at Shanghai ‘carnival’ amid China’s push for embodied AI
Trust79 - Aug 24, 2026 · MIT Technology Review — AI
Why children outperform AI in language learning remains unresolved
Trust79