Runway Just Solved AI Video’s Biggest Problem

Runway AI has launched its Gen-4 video generation model, offering a big breakthrough in maintaining character and scene consistency across multiple shots. Unlike previous AI video systems, Gen-4 creates continuous visual narratives by preserving objects, characters, and styles throughout various angles and lighting conditions. This model tackles a significant flaw in AI video production, ensuring that characters and settings remain consistent in every frame which is an important factor for believable storytelling.

Available to paid subscribers and enterprise clients, Gen-4 uses reference images combined with text prompts to generate high-quality, realistic motion in video clips. Runway has demonstrated this model through short movies, resembling “Latest York is a Zoo,” showcasing consistent visual effects. As the corporate pushes forward with an entire digital production pipeline, the discharge of Gen-4 marks a pivotal moment in AI filmmaking. Read more.

OpenAI has made ChatGPT’s latest image generation tool available at no cost, following an initial delay. CEO Sam Altman confirmed the tool’s availability to free-tier users, albeit with unspecified limits. He also warned that capability constraints will delay upcoming product releases, citing overwhelming demand. The GPT-4o-powered model, known for Studio Ghibli-style recreations, was postponed after ChatGPT gained one million users in an hour.

ChatGPT’s subscriber now exceeds 20 million paying users—a 4.5 million surge since last yr. This translates to an estimated $415 million in monthly revenue, setting OpenAI on the right track for an enviable $12.7 billion in annual earnings. The corporate has also just wrapped up a $40 billion funding, the biggest private tech deal on record, led by SoftBank, with Microsoft and others in tow. But SoftBank’s hefty $30 billion stake is contingent on OpenAI hitting its for-profit goal by yr’s end.

OpenAI’s next move is to release an open-weight AI model—its first since GPT-2. It’s a strategic counterpunch to Meta’s Llama, which imposes deployment limits. They’re currently gathering feedback through global developer sessions to refine this open model. It has also launched a free learning platform for AI skills with OpenAI Academy.

Nonetheless, OpenAI isn’t any stranger to controversy. A recent report claims its GPT-4o model was trained on O’Reilly’s paywalled books without consent, a move that’s drawing further scrutiny and will ignite recent legal fires. With all eyes on its next steps, the corporate continues to balance progress with the growing legal and ethical tightrope it’s walking. Read more.

Luma Labs introduces Camera Motion Concepts for its Ray2 video model. This innovation allows users to direct precise, cinematic camera movements via natural language commands, utilizing over 20 precision-tuned motions. The feature, now available on Dream Machine, employs “Concepts,” a novel method for teaching generative models recent controls from minimal examples.

Unlike LoRA or finetuning, Concepts enable composition of multiple motions without degrading Ray2’s core quality. This facilitates unique, combinatorial camera moves, including those physically inconceivable. The technology maintains Ray2’s high-fidelity output and stylistic versatility. Read more.