Training in the application of artificial intelligence in video production has become increasingly essential. AI has permeated various aspects of life and has had a significant impact on media practice, particularly in enhancing production speed, improving the quality of media outputs, and fostering innovation in both form and content.

Given that media professionals rely extensively on visual content—especially video in its diverse formats, and more specifically short-form video suited to the dynamics of social media platforms—this training is now a strategic priority for strengthening the capacities of media students and journalists. It equips them with advanced competencies in producing visual content using the latest generation of generative AI models, notably Kling, Google Veo 3.1, Seedance 2.0, and the Multi-Reference Guidance system for ensuring visual continuity across scenes.

Furthermore, the training develops specialized skills, including prompt engineering using the Shot Grammar framework, techniques for maintaining character identity consistency across multiple shots, prompt chaining for constructing coherent narrative sequences, Arabic voice-over generation, and professional-level post-production editing.

• principles of artificial intelligence (ESCO)
• video-games functionalities (ESCO)
• video-games trends (ESCO)
• music and video industry (ESCO)
• emergent technologies (ESCO)
• data mining (ESCO)

• develop investigation strategy (ESCO)
• develop military intelligence records (ESCO)
• supervise video and motion picture editing team (ESCO)
• teach computer science (ESCO)
• coordinate sale of video and motion picture production products (ESCO)
• perform video editing (ESCO)
• work with video and motion picture production team (ESCO)
• watch video and motion picture production products (ESCO)
• perform data mining (ESCO)

Media students.

Journalists

Basic knowledge of AI concepts

Basic skills in video production

25 Hours

Understanding AI-based models for generating images and videos, including animation and motion synthesis techniques.

Mastering prompt writing for each model, and learning how to maintain visual consistency of characters across AI-generated videos and images.

Generating visual effects and editing videos using artificial intelligence tools and workflows.

Applying ethical principles in AI-based video production, including responsible use, transparency, and awareness of issues such as deepfakes and intellectual property rights.

The assessment is based on three components. The first component (25%) consists of progressive practical assignments completed during and between training units. These include writing cinematic prompts according to the Shot Grammar framework, generating a four-shot visually consistent scene featuring one or more characters, and integrating audio with the generated video.

The second component (25%) is a digital portfolio, in which participants document their developmental journey throughout the program. It includes their best outputs accompanied by reflections on prompts, design choices, challenges encountered, and the solutions applied.

The third component (50%) is a final integrated project (a short video or AI-generated visual report). It is evaluated according to six criteria: visual generation quality, cross-scene consistency, prompt effectiveness, audio integration quality, narrative coherence and editing, and adherence to ethical standards.

The required passing score is 60% of the total marks.

• knowledge engineer (ESCO)
• video designer (ESCO)
• ICT intelligent systems designer (ESCO)
• post-production supervisor (ESCO)
• intelligence officer (ESCO)