Aleph can generate new camera angles from a single shot, apply style transfers while maintaining scene consistency, and add or remove elements from scenes.

Other editing features include relighting scenes, creating green screen mattes, changing settings and characters, and generating the next shot in a sequence.

Early access is rolling out to Enterprise and Creative Partners, with broader availability eventually for all Runway users.

Wan2.2 uses two specialized "experts" — one creates the overall scene while the other adds fine details, keeping the system efficient.

The model surpassed top rivals, including Seedance, Hailuo, Kling, and Sora, in aesthetics, text rendering, camera control, and more.

It was trained on 66% more images and 83% more videos than Wan2.1, enabling it to better handle complex motion, scenes, and aesthetics.

Users can also fine-tune video aspects like lighting, color, and camera angles, unlocking more cinematic control over the final output.

Showrunner launches publicly this week with two original show offerings where users can steer narratives and create episodes within established worlds.

Users can also upload themselves as characters, with Fable saying the future of animation is “remixable, multiplayer, personalized, and interactive” content.

The platform will be free, with an eventual monthly fee for generation credits — with plans to enable revenue sharing for creators when their content is remixed.

Showrunner initially went viral in 2023 after releasing an experiment of personalized (but unauthorized) South Park episodes.

Study Mode uses custom instructions created with teaching experts to ask guiding questions and provide interactive learning instead of direct answers.

The AI guides learners with interactive prompts, hints, and knowledge checks to encourage active participation and deeper understanding.

ChatGPT will actively resist requests for quick solutions in this mode, instead redirecting students back to the learning process.

The rollout begins immediately for Free, Plus, Pro, and Team users, with educational institutions receiving access within the next few weeks.

The model was trained on a diverse, curated dataset to avoid common AI outputs like waxy skin, blurry backgrounds, and oversaturated colors.

The companies call FLUX.1 Krea SOTA amongst open models, while rivaling top closed systems (like BFL’s own FLUX 1.1 Pro) in human preference tests.

The release is fully compatible with the FLUX.1 [dev] ecosystem, making it easy to integrate for developers and within other applications.

Meta CEO Mark Zuckerberg just announced that former OpenAI researcher Shengjia Zhao will serve as chief scientist of the newly formed Meta Superintelligence Labs, bringing his expertise on ChatGPT, GPT-4, o1, and more.

Alibaba launched an update to ‘Qwen3-Thinking’, now competitive with Gemini 2.5 Pro, o4-mini, and DeepSeek R1 across knowledge, reasoning, and coding benchmarks.

Tencent released ‘Hunyuan3D World Model 1.0’, a new open-source world generation model for creating interactive, editable 3D worlds from image or text prompts.

Google has rolled out 'Video Overviews' in NotebookLM. The feature uses AI to create narrated slideshows with visuals, diagrams, and data pulled directly from your documents.

Fundamental Research Labs just unveiled ‘Shortcut’, an AI agent for Excel. The company claims the tool beats first-year analysts from McKinsey and Goldman in 89.1% of head-to-head comparisons.

Music company Hallwood Media signed top Suno ‘music designer/creator’ Imoliver in a record deal, becoming the first creator from the platform to join a label.

Alibaba debuted ‘Quark AI glasses’, a new line of smart glasses launching by the end of the year, powered by the company’s Qwen model.

Midjourney introduced ‘start & end frame’ control. A new AI video feature that lets users generate clips with custom start and end images, allowing for smoother transitions and seamless loops.

Adobe has launched new AI-powered Photoshop tools in beta that will allow users to enhance images without quality loss — perfect for reviving old and vintage photos.

Ideogram released ‘Character’, a character consistency model allowing users to place a specific person into existing scenes and new outputs from a single reference photo.

Agentic AI startup Manus launched ‘Wide Research’, a feature that leverages agent-to-agent collaboration to deploy hundreds of subagents to handle a single task.