Translating the full HTML now—visible copy only, structure and English prompts untouched.
Tool guide · Xiaohu Explains
Magnific's image and video handbook: direct the scene, not a keyword pile
Original prompts, banned-word lists, and camera rules you can copy off the page—treat the model rankings as Magnific's own take; they never published a methodology.
⚑ Read this first: Magnific's own team wrote the handbook. The model list is whatever ships on their platform—Midjourney, Imagen, Runway, and Veo aren't on it, and the last page is "book a demo." "In our tests" shows up often, with no sample size, scoring method, or who judged. Take "which model is strongest" as field notes, not a lab ranking. The methods—how to describe a scene, kill the AI look, join shots—don't depend on the platform. That part is the real payload.
Background
What the handbook covers: image, video, and film-grade camera moves
Magnific released a free 38-page prompting guide, The Prompting Handbook. It covers more than stills—it fills in AI video generation and film-style director control over camera moves. The thesis: AI is fully in the reasoning era—you brief models like a director. Drop the dead keywords. Steer with clear, professional visual language.
Primary source and reference
- Magnific Academy Original publisher