Official Prompting Guide for Sora 2 by OpenAI
Structure:
— General Scene and Description:
• Describe the scene in simple language;
• Specify characters, costumes, set design, weather, and other details;
• Be as detailed as necessary to create a video that matches your vision.
— Cinematography:
• Shot type and camera angle: specify, for example, “wide shot, eye level” or “close-up, slight tilt from behind”;
• Mood: define the overall tone, e.g., “cinematic and tense,” “playful with tension,” “luxurious anticipation”;
• Lens and filtering: you can specify the type of lens and filters, e.g., “32mm / 50mm spherical lenses, light CPL filter”;
• Lighting and palette: describe the quality of light and main colors, e.g., “soft daylight from a window with warm fill light from a lamp and a cool reflection from the hallway.”
— Actions:
• List clear, specific actions or gestures as bullet points;
• Try to describe actions as distinct moments or beats tied to time.
— Dialogue:
• If there’s dialogue in the shot, include short, natural lines;
• Keep them concise so the timing fits the clip’s duration.
— Background Sounds:
• Describe ambient sounds that help set the rhythm or atmosphere;
• For example, “hum of coffee machines and murmuring voices” or “rustling paper and footsteps.”

https://cookbook.openai.com/examples/sora/sora2_prompting_guide

Veo 3.1
Leaks from Twitter on October 8, 2025, indicate an upcoming Veo 3.1 update for Google’s video generation model, spotted in the Higgsfield AI waitlist and internal codebases such as Vertex AI. The rumored improvements include enhanced character consistency, video durations of up to one minute, scene builders, and cinematic presets. The AI community views these as steps aimed at challenging OpenAI’s Sora, although Google has not provided official confirmation.

Veo 3.1 has appeared on Google Flow.

Google Flow has introduced video editing features.
One of the cool ones: object insertion — you just choose where you want to place the object and describe it. Flow will generate the object and seamlessly integrate it into your clip.

WOW! First time in the Longshot: Full 1 Minute AI Movies From One Prompt, with consistent characters. Forget those 5-second clips, it’s time for real storytelling.

With Longshot, you can generate a full 1-minute cinematic video complete with music, dialogue, and consistent characters — all from a single prompt. Type your story, upload your hero, and watch it come alive like a movie.

Try it now: https://vortex.channel/longshot

They’re adding video upscaling to Grok.
But it’s only for Grok Imagine Videos, meaning videos generated within Grok itself.
And apparently, it’s only available in the desktop version.
It upscales to HD in about 10 seconds.

Imagine typing a simple idea — and watching it come alive as a full cinematic scene with acting, lighting, motion, and emotion. No crew. No animation tools. Just pure AI filmmaking. Welcome to Vidu Q2, the next-generation AI model that transforms imagination into real moving cinema. In this episode, we explore what makes Vidu Q2 revolutionary — from its Reference-to-Video (reference to the video) system that blends up to 7 reference images into one coherent video, to its upgraded Image-to-Video engine that brings unmatched motion realism, stable faces, and emotional depth. Vidu Q2 doesn’t just generate clips — it performs them. With real camera work, micro-expressions, and fluid storytelling, this model is redefining what “AI video generation” means.
https://www.youtube.com/watch?v=hEbtpJIYcLo