Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
Introducing a more powerful NotebookLM 🚀
Massive upgrades deliver agentic capabilities in chat, more advanced reasoning, and a suite of new output formats. Tackling complex, multi-step research problems has never been easier.
Rolling out now to Google AI Ultra subscribers.
Step 3
Upload the marked image and add a motion prompt.
Prompt structure I used:
Please remove the red line, arrows, and all guide marks from the final video. The red path is only used as camera motion guidance.
Create a first-person FPV drone shot with cinematic, ultra-fast, one-take motion. The camera should follow the red path on the image closely. Keep the route order. No skipped segments, no simplified path.
The camera starts near Mt. Fuji, orbits the summit, then dives down through the residential area and trees. It flies toward the Eiffel Tower, passes through the base, spirals upward around the tower, then dives toward the Colosseum. It enters through the broken opening, turns inside the arena, exits, and flies toward the Statue of Liberty. Finally, it rises around the statue and stops at a high overhead angle, showing the Statue of Liberty, Colosseum, Eiffel Tower, and Mt. Fuji in one final view.
Ultra-realistic, smooth motion, strong speed, clear spatial continuity. No red lines, no arrows, no text, no watermark, no duplicated landmarks, no distorted buildings.
If this gives you ideas, follow @MrLarus .
I’ll keep sharing more AI workflows, prompt tests, and creative production cases.