
Discover the fascinating world of artificial intelligence applied to the audiovisual field. Learn to use generative AI tools to enhance your creative projects and explore new narrative possibilities. With a combination of theory and practice, delve into the creation of unique audiovisual content, improving both visual quality and the efficiency of the production process. From generating images and videos to integrating music and sound effects, each lesson will introduce you to the most advanced and effective techniques.
Take advantage of the One open source model, which offers you the flexibility to work in the cloud or on your own computer. Become an expert in implementing AI technologies in your projects, optimizing resources and achieving surprising results. Ideal for filmmakers, documentary filmmakers, and creatives in the advertising world, this course provides you with the tools and knowledge necessary to take your productions to the next level. Prepare to innovate and transform your approach to audiovisual content with the latest trends in artificial intelligence.
7 lessons & 1 download

10 minutes, 10 seconds

16 minutes, 29 seconds

18 minutes, 13 seconds

6 minutes, 56 seconds

3 minutes, 13 seconds
You'll learn how to integrate artificial intelligence tools into your audiovisual projects, expanding your creative skills to new heights. You'll discover how to use open-source models to transform images into videos and generate stunning visual content. You'll learn techniques to optimize the quality of your productions, from choosing the right prompts to applying video interpolations, thus increasing the visual impact of your work.
In addition, you'll master the use of platforms and software that will allow you to create and edit music and audio with artificial intelligence, elevating the sound quality of your projects. You'll explore how to generate realistic voiceovers and how to synchronize these voices with images to bring your narratives to life. Upon completion, you'll have a solid set of tools and knowledge to continue independently exploring the fascinating world of AI-assisted audiovisual creation.
The project consists of creating a short documentary about a fox, exploring everything from the initial idea to the final edit. You'll learn to generate visual and audio content using artificial intelligence tools, mastering lip-syncing and video editing techniques.
This course is designed for audiovisual creatives and artificial intelligence enthusiasts who want to explore new generative tools, technologists interested in open source models, and film and advertising professionals looking to innovate their visual productions.
No extensive prior knowledge is required, but a computer with good graphics capabilities, preferably an Nvidia 4090 or similar card, is essential. Access to tools like One and video editing software like Premiere is also necessary.
Muy bien explicado y muy interesante
Buen curso explicado.
Es un curso muy interesante donde aporta diferentes herramientas para la creación mediante la AI, y como introducción a este campo es de gran ayuda.
Gran introducción para iniciar con video AI. La propuesta es crear un mockumentary de 30 segundos. Toca muy rápido desde el guión, el desarrollo del storyboard, la creación de las imágenes, crear las secuencias de videos, generación de música para el mockumentary, hasta el audio dubbing en diferentes plataformas. Me encantaría una segunda o tercera parte profundizando cada una de las etapas. Sin dudas, te da unas bases para empezar. Les recomiendo grok imagine para la generación de video.

Mockumentaries with Artificial Intelligence and WAN Video
Enjoy learning from home without a set schedule and with an easy-to-follow method. You set your own pace.
Learn valuable methods and techniques explained by top experts in the creative sector.
Each expert teaches what they do best, with clear guidelines, true passion, and professional insight in every lesson.
If you're a Plus member, get a custom certificate signed by your teacher for every course. Share it on your portfolio, social media, or wherever you like.
Videos of the highest quality, so you don't miss a single detail. With unlimited access, you can watch them as many times as you need to perfect your technique.
Ask questions, request feedback, or offer solutions. Share your learning experience with other students in the community who are as passionate about creativity as you are.
The community is home to millions of people from around the world who are curious and passionate about exploring and expressing their creativity.
Domestika curates its teacher roster and produces every course in-house to ensure a high-quality online learning experience.
Wan Video is an open source AI model that lets you generate and animate videos from images, text, or reference videos, making it easier to create innovative, automated audiovisual content.
This course is aimed at people with intermediate knowledge of audiovisual production and editing, though key concepts are explained for those with basic experience in AI or video editing.
To run Wan Video locally, a Nvidia GPU with at least 24 GB of VRAM and CUDA-compatible systems are recommended; editors like Premiere and platforms like ComfyUI are also used.
You’ll learn to install and use models like Wan Video, generate videos from images, text, and video, sync audio and lip movements, edit and optimize videos, create storyboards and animatics, and explore open source alternatives.
With Wan Video, you can analyze the motion in a reference video and apply it to a still image, creating a realistic animation of the character or element in the picture.
Besides Wan Video, there are models like Runway’s Act 2 and various ComfyUI integrations, each with unique features and options for local or cloud use.
Using Wan Video in the cloud offers easy access without hardware requirements but with limited credits; running it locally gives you full control and unlimited use if you have the right hardware.