Arte, tecnología e inteligencia artificial en la narrativa audiovisual contemporánea

Art, technology, and artificial intelligence in contemporary audiovisual narrative

Primer plano de un artista digital trabajando con herramientas de inteligencia artificial y diseño 3D en su estudio.
Interviewee
Juan Carlos Abraldes · Art Direction & Visual Development · AbraldeStudio
Category
Tecnología creativa y difusión digital
Published
2026-09-17

Pedro Ortega: Your career stands out for combining a solid artistic vision with high technical expertise, working with both traditional media and real-time virtual production and generative tools. What was your initial training in artistic disciplines like, and how has that traditional base allowed you to adapt to such an advanced technological environment?

Juan Carlos Abraldes: My artistic training begins in sculpture. I am a sculptor by training and, from very early on, I felt curious about practically all artistic disciplines: classical drawing, painting, illustration, comics… For many years I worked mainly as a cartoonist and illustrator for different magazines and newspapers, while combining that activity with painting exhibitions. I was also a founding partner of the 2D animation studio Tangaraño, where I was involved for approximately three years.

That stage was very important for me because it allowed me to understand that, regardless of the discipline, behind any image there is a series of common areas of knowledge: composition, perspective, proportion, anatomy, volume, light, color, visual narrative and, above all, the capacity for observation. That knowledge is what really builds an artist's gaze.

In the late nineties, I began to receive offers from different 3D animation companies proposing that I join their teams and adapt my way of working to those new processes. And my initial reaction was quite negative. I came from a completely manual work philosophy and, at that time, I perceived that technology as a threat to a profession to which I had dedicated many years. I thought it could end up degrading precisely what for me constituted the value of artistic work: mastery of the hand, of drawing, and of traditional procedures.

But around 2004, a fundamental change occurred in my way of understanding it. I realized that the arrival of 3D technology was not a passing fad nor something it made sense to fight against. It was a profound transformation of the industry and, quite simply, it could not be stopped.

From that moment on, I made a decision that has conditioned my entire subsequent career: to stop considering technology as a problem and start considering it as a tool. Since then, I have tried never to waste time resisting changes. Every time a new process, a new tool, or a new technology appears, my first reaction is to try to understand what it can contribute to my work and how I can incorporate it into my artistic language.

And there is something that is fundamental to me: this technological evolution has never meant abandoning my traditional training. On the contrary. Classical art remains the foundation today upon which I build everything else. When I work with 3D, virtual production, real-time engines, or generative artificial intelligence, I continue to make decisions based on the same knowledge I acquired drawing, painting, and sculpting: how a shape works, how light hits it, how a composition is built, how the viewer's gaze is directed, or how an image can convey a certain emotion.

That's why I don't see my career as a transition from analog to digital, but as an accumulation of tools. Technology has changed a lot, but the fundamentals of visual language remain the same.

In fact, I believe that my own experience with 3D taught me a lesson that I apply today to artificial intelligence as well: it doesn't make much sense to ask if a new technology is going to replace the previous one. The interesting question is what we can do with it and what new possibilities it allows us to develop as artists.

Today I can work with tools that thirty years ago seemed like science fiction, but I still face an image with the same essential questions as when I had a pencil, a brush, or a sculpting tool in my hands. Technology can change the process; what should not change is the artist's ability to look, decide, and tell.

PO: On your YouTube channel and your portfolio, we find a wide variety of cinematic narrative projects and even storyboards. When facing these projects, how do you manage to combine your work moving between such different formats, ensuring that each proposal becomes a unique visual experience?

JCA: I think the answer lies, above all, in the years of experience and in having had the opportunity to work in many different disciplines within audiovisual production. Over about twenty years, I have been able to develop different functions in various production companies and, since 2015, also from my own studio, AbraldeStudio. That trajectory has allowed me to know projects not only from an artistic perspective, but also from many of the stages that make it possible for an idea to finally become an image.

I have had the opportunity to participate in projects from very early stages, preparing proposals and developing concepts, but also writing scripts, creating designs, modeling, texturing, animating, and lighting. I have worked with different 3D tools and software, with graphics engines like Unreal Engine and, currently, with generative artificial intelligence tools, which I understand as an enhancer of all that previous knowledge and as one more tool within the process.

I believe that this transversal experience is precisely what allows me to jump from one format to another quite naturally. A storyboard, concept art, character design, a 3D environment, a cinematic sequence, or a real-time experience may seem like very different jobs, but for me they are part of the same process: visually building an idea and making that idea work.

Furthermore, having worked in different specialties has given me a fairly general view of the pipeline. When I design something, I don't only think about whether it works as an image. I also think about what will happen next with that design: how it could be modeled, how much time it might require, how it can be lit, how it would work in motion, what problems it might generate in production, or how it could be optimized for a real-time engine.

That also allows me to understand the needs of other disciplines. I can propose a solution from the perspective of the modeler, the animator, the lighter, or the artistic director because, to a greater or lesser extent, I have passed through those disciplines. And I think that global vision is especially important when working on complex projects, because many times a good decision made in an early phase can save a huge amount of time and problems in later phases.

That's why I try to give each project its own identity, but without losing sight of something that is fundamental to me: consistency between all its parts. Image, design, narrative, technology, and production have to work in the same direction.

In that sense, I believe that current technology, including artificial intelligence, enormously expands the possibilities, but it does not replace that global vision. On the contrary: the more tools we have available, the more important it becomes to know what we want to achieve with them.

In the end, my work consists of moving between disciplines without losing sight of the whole. And that is probably one of the things I have learned most during these years: understanding not only how to do a certain part of a project, but how to make each part help improve the others.

PO: Your studio, AbraldeStudio, is characterized by incorporating design enhanced by artificial intelligence and generative tools alongside traditional techniques. How was your first professional contact with these technologies and what led you to decide that they should become a pillar of your workflows instead of being a mere experimental resource?

JCA: My first contact with generative artificial intelligence was, in fact, quite progressive. Around 2021, I started to see the first works being done with these technologies, but at that time they didn't particularly surprise me, nor did I think they would have such a profound impact on my profession. I saw it as something interesting, but still quite experimental.

The change came in 2022, when I started working at Replikant as a developer artist for the procedural animation software Replikant, based on Unreal Engine. There I had my first real professional experience with artificial intelligence and I could see that its potential went much further than generating an image from text.

At Replikant, AI was used to power different parts of the creation process: from conceptual development to the generation of voices, scenes, or certain processes related to lighting. We also worked with a version called Replikant Chat, which allowed for an especially interesting experience because it made it possible to interact in real time with 3D characters within the engine environment itself.

It was important for me to live that experience from the inside, because I began to understand that AI didn't necessarily have to be an isolated tool used at the beginning or end of a project. It could become a transversal layer capable of intervening at different moments of the production process and, above all, it could establish a much more direct relationship between creative intention and its execution.

I was working at Replikant for almost four years. That period was fundamental in changing my perception of these technologies. If at first I saw AI as something experimental, there I was able to verify that it could be integrated into a professional workflow and be part of real production processes.

From then on, I continued developing my own workflows with generative tools and, subsequently, that experience also became part of AbraldeStudio's philosophy. But there is one issue that is essential to me: I have never understood artificial intelligence as a substitute for my work as an artist.

I use it as an enhancer.

My training and my artistic criteria are still the starting point. AI can help me explore more possibilities, iterate faster, try solutions that might otherwise require much more time, or even open up visual paths that I hadn't initially contemplated. But the decision of what works, what doesn't work, what I want to tell, and what the visual language of a project should be remains an artistic decision.

In fact, the more I work with these tools, the more convinced I am that previous experience is important. AI can produce images in seconds, but that doesn't mean all those images are useful. Knowing how to select, correct, transform, combine, and direct those results requires criteria and knowledge.

That is why at AbraldeStudio, artificial intelligence is not proposed as a replacement for traditional techniques, but as a tool that coexists with them. I can start from a drawing, a photograph, a sculpture, a 3D model, an Unreal scene, or a conceptual idea and use different generative tools to take it in different directions.

For me, the real leap does not consist simply in a machine being able to generate an image. What is truly interesting is that now we can build hybrid processes in which artistic knowledge, 3D, real-time, and artificial intelligence work together.

And that is probably the reason why it stopped being an experimental resource for me: when you understand that a technology can be integrated coherently within your creative process and increase your possibilities without taking away artistic control, it stops being a novelty and becomes simply another work tool.

PO: In your productions and visual tests, there is a strong inclination towards futuristic and science fiction aesthetics. As a visual artist specialized in cinematic narrative, what do you consider to be the true potential of generative AI to expand world-building and the development of complex environments in films and short films of this genre?

JCA: I am very interested in fantasy, science fiction, and horror cinema, but perhaps what attracts me most is cinema that uses these genres to explore the human mind, society, fears, and the different realities we can build within our own perception. I am especially interested in the dreamlike and surreal world, and in that sense, David Lynch's cinema has always been a reference for me.

I believe that precisely in these territories, generative artificial intelligence can have enormous potential. Not only because it allows producing images very quickly, but because it allows visually exploring ideas that until very recently were difficult, slow, or economically unfeasible to develop. We can imagine architecture, a city, a landscape, a creature, or even a complete reality and start experimenting with it practically from the moment the idea arises.

But I think its true potential lies in something deeper: AI is beginning to affect practically the entire creation pipeline. We are no longer talking only about generating a conceptual image. It can intervene in the development of characters and environments, in the creation and treatment of assets, in certain modeling and texturing processes, in animation, in lighting, in editing, and in post-production. It can also automate certain technical and repetitive tasks that traditionally consumed a huge amount of hours.

This can greatly change the way a cinematic world is built. We can start from a conceptual idea, develop it visually, then take it to a three-dimensional environment, incorporate it into a real-time graphics engine, test different lighting, cameras, and atmospheres, and then continue modifying or perfecting certain elements during post-production. The process begins to be much more flexible and, above all, much more iterative.

I also find the evolution we are seeing in image and video restoration and treatment tools very interesting. AI no longer just creates new content: it can also recover information, increase resolution, reduce noise, reconstruct details, or improve material that previously would have been very difficult to take advantage of.

And this is especially important for science fiction and fantasy, because it allows reducing some of the economic and technical barriers that have traditionally limited imagination. When producing a certain environment no longer requires months of work to see if an idea works, the artist can afford to experiment much more.

For me, world-building does not consist simply of creating spectacular settings. A world has to have an identity, rules, an atmosphere, and internal logic. It has to serve the story and, in certain cases, even convey the psychological state of the characters.

That is where I find a very interesting connection with David Lynch. In his cinema, an apparently everyday space can be transformed into something disturbing, surreal, or deeply psychological. Architecture, lighting, sound, and objects cease to be simply decorative and become part of the narrative. AI can offer us an extraordinary capacity to explore precisely those kinds of possibilities: not just what a world would look like, but how it could feel.

I think that is the real change. Technology is reducing the distance between imagining something and being able to visualize it. And the smaller that distance, the greater our capacity to experiment, make mistakes, go back, and find solutions that before we might not have even dared to propose.

But I still think that technology is only the medium. It can generate thousands of possibilities, but someone has to decide which of them really belongs to the story. The future that interests me is not automatically generated cinema, but cinema in which artists, technicians, and new tools can work together to build worlds much more complex, personal, and difficult to imagine until now.

PO: AbraldeStudio offers visual development and concept art services for video games using real-time technology and testing with advanced tools like metahumans. How is AI transforming the creation of interactive assets and how is it integrated with real-time rendering engines to speed up the production of virtual worlds within the video game sector?

JCA: I think we are moving from a fundamentally manual creation model to another in which generation and optimization are increasingly assisted by artificial intelligence. Today there are tools capable of generating certain 3D assets in a matter of seconds with sufficient quality to use them as a starting point in a film production or a video game.

But for me, the important thing is not just the speed of generation. What is truly interesting is how this technology can transform the entire creation pipeline of a virtual world.

Traditionally, an asset could require many hours of work: modeling, retopology, UVs, texturing, materials, different levels of detail and, in the case of characters, rigging and animation. AI is beginning to automate or accelerate many of those tasks. It can generate geometry, propose topological structures, create physically consistent materials and textures, or even help prepare characters for animation. That doesn't mean the artist disappears from the process; it means they can spend less time on purely mechanical tasks and more on deciding what the asset should be and how it should function within the universe we are building.

We are also seeing significant advances in animation. From video captured with relatively simple means, certain systems can interpret human movement, generate animations, and help correct capture problems. This opens up huge possibilities, especially for small teams.

But the true revolution appears when all this is connected with real-time rendering engines. There we can start with a visual concept, convert it into a three-dimensional asset, incorporate it into the environment, immediately test different materials, lighting, cameras, and behaviors, and check in real time how it works within the world.

Even the creation of large environments can benefit from this combination of AI and procedural generation. Instead of manually placing each element of a stage, we can establish certain rules and let the system help us populate large surfaces with vegetation, rocks, buildings, architectural elements, or other objects while maintaining certain distribution and consistency criteria.

This also changes the prototyping phase. Before, you might need weeks to build an environment elaborate enough to know if a certain idea worked. Now a small team can quickly set up a first version of the world, test it within the engine, and start making decisions about it practically from the first moment.

And for me, there is something especially interesting about this: AI is starting to become a kind of bridge between disciplines. A designer can propose an idea, an artist can develop it visually, a modeler can convert it into geometry, the engine can integrate it in real time, and certain AI tools can help automate parts of that journey.

This doesn't mean that all these processes are completely automatic or that the results generated by AI are always ready for production. There is still an enormous need for supervision, correction, optimization, and artistic direction. But the speed at which we can move from an idea to a prototype is completely different.

I believe this has a very important consequence for the future of video games: relatively small teams can start to tackle projects and worlds that previously required much larger production structures. Technology does not eliminate the complexity of creating a video game, but it can shift many of the bottlenecks that for years have limited that production.

In the end, we return to the same issue: AI can generate an asset, but it doesn't necessarily know why that asset should exist, what narrative function it has, what visual language it should follow, or how it should relate to everything else. That vision of the whole still depends on the artist and the creative team.

That's why I see AI as a capacity multiplier. It doesn't replace the artist's knowledge; it allows that knowledge to be applied at a scale and speed that until very recently were difficult to imagine.

PO: As a Senior Visual Artist focused on leading creative teams, defining artistic style, and guiding projects from the initial concept to the final assets, how do you think your role changes with the emergence of AI? Although a machine can generate images in seconds, why are human vision, aesthetic criteria, and direction still irreplaceable for giving soul and consistency to a story?

JCA: I think my role changes, but not necessarily in the sense that it is going to disappear. On the contrary: I think that as artificial intelligence tools increase our production capacity, the figure of the artist and, especially, of the person who visually directs a project acquires even greater responsibility.

I would use a very simple metaphor: the artist increasingly becomes an orchestra conductor. AI provides us with a huge number of instruments and can execute certain tasks at an extraordinary speed, but someone has to decide which instruments to use, how to combine them, at what moment and, above all, what we want to transmit.

I am convinced that artificial intelligence is going to transform many jobs and that some specific functions will be automated. It would be naive to deny that reality. But I also don't believe that there will be a massive disappearance of professionals in the proportion that is sometimes announced. I think we are moving towards a different model.

I imagine that, within each specialty, professionals will have more and more AI agents and tools working alongside them. A modeler may have systems that help them with certain technical tasks; an animator may have tools capable of interpreting and correcting movements; a conceptual artist will be able to explore hundreds of possibilities in a very short time. AI can make each professional much more flexible, productive, and capable of tackling problems that previously required much more time or even the intervention of several people.

But there is a fundamental difference between producing and directing.

A machine can generate hundreds of images, but it doesn't necessarily know which of them belongs to our story. It can produce a technically correct solution, but that doesn't mean it's the right solution from a narrative, emotional, or artistic point of view.

When a professional project needs consistency, someone has to establish a visual language and maintain it throughout the entire process. You have to decide what is accepted and what is discarded, correct errors, detect inconsistencies, modify a composition, adjust lighting, change an expression, or ensure that a character, a setting, and a sequence appear to belong to the same universe.

And that is where human intervention remains essential. Even when a tool can do much of the work automatically, the result often needs to be reviewed, corrected, and directed. The last part of the process, the one that consists of deciding if it really works, can be much more important than the generation itself.

That is why I believe the value of the artist is not going to disappear; it's going to shift. Perhaps in the future we will spend less time executing certain tasks and much more time thinking, selecting, directing, correcting, and making decisions.

In my case, that means my work as a Senior Visual Artist doesn't just consist of knowing how to produce an image. It consists of having a vision broad enough to know where a project should go and ensuring that all the tools and all the people participating in it move in the same direction.

AI can enormously accelerate execution, but the baton still has to be in someone's hands.

And I believe that the more powerful the technology, the more important precisely that capacity for direction, criteria, and vision will be. Because when we can generate practically anything, the real problem stops being how to produce an image and becomes deciding which one is worth producing.

PO: The adoption of generative AI in entertainment has sparked deep concern about the labor future of traditional illustrators and concept artists. From your position at the head of a studio, what do you consider to be the main labor and ethical problems brought about by this transition, and how do you think the industry should balance technological efficiency with the protection of human talent?

JCA: I think that, at an ethical and labor level, we are living through one of the most important paradigm shifts of our time. The controversy is enormous and we are probably still very far from having found a balance. Artificial intelligence is entering practically all sectors of society and I think it would be very difficult, if not impossible, to try to put barriers to a technological transformation of this magnitude.

That doesn't mean there shouldn't be regulation. I think it has to exist, especially to protect rights, establish responsibilities, and avoid abuses. But I think regulation should not be considered a way to stop technology, but rather a way to ensure its incorporation into society and industries is as fair and balanced as possible.

In the audiovisual sector, I think that, to a certain extent, we are framing the problem wrong. The idea has spread that since anyone with access to these tools can currently generate a spectacular image or even a surprising video, traditional artists, illustrators, concept artists, directors, or filmmakers are inevitably going to be displaced.

I am not so convinced of that. In fact, I think something quite different may happen.

When a tool is democratized and everyone has access to it, the tool stops being the differentiating element. In a few years, generating a certain image with AI will probably be as common as using an editing program or a digital camera today. What will make the difference will be what each person does with that technology.

And that's where I think professionals with a solid artistic background will have an enormous advantage. An artist who knows drawing, composition, light, color, anatomy, visual narrative, design, and artistic direction can use AI in a completely different way than someone who simply learns to write an instruction to get an image.

AI can give you possibilities, but it cannot automatically provide you with a personal vision.

That's why I don't think the future belongs to those who simply know how to use a certain tool better. I think it will belong to a new generation of creatives capable of combining solid training with these technologies and using them to develop new visual languages and new ways of telling stories.

This also has a price. Training can no longer end when you finish your studies. Constant updates will be part of the profession. You will have to continuously learn new tools, new processes, and new ways of working, but you will also have to further develop creative capacity and your own judgment.

And there is another issue that seems fundamental to me: I don't think everyone who uses AI is going to be part of this artistic revolution. Just as the appearance of photography, cinema, animation, or digital tools did not automatically turn everyone into a photographer, filmmaker, or artist, AI is not going to turn just anyone into a great creator either.

I think we are facing the possibility of a real artistic revolution, but it will probably be led by a minority of people capable of using these tools to create something that doesn't yet exist, and not simply to reproduce what we already know.

For a time, I thought that the reaction against AI might provoke a renaissance of traditional artistic disciplines: a kind of claim for painting, sculpture, or drawing as a human response to technology. I thought new artistic movements could appear that defended precisely the manual and the human.

So far, I am not seeing that revolution with the intensity I imagined.

What I am seeing is another possibility: that the great artistic revolution occurs precisely among those creators capable of using AI as an extension of their own creativity.

And that, for me, is what is truly interesting. I don't think we are just facing a new production tool. I think we are facing the appearance of a new language. And as has always happened in the history of art, it will probably be a few creators who manage to master that language, develop their own voice, and open paths that will eventually influence everyone else.

That is why I believe the best way to protect human talent is not to pit it against technology, but to ensure that artists have the training, tools, and conditions necessary to actively participate in this transformation. The question shouldn't be AI versus artists, but what artists can achieve when they have a technology capable of multiplying their capabilities.

PO: Finally, let's look at the positive side: what are the most tangible advantages that AI-assisted design brings you today, and how do you imagine the medium-term future of hybrid audiovisual production? What future do you predict for the sector?

JCA: One of the most tangible advantages that AI currently brings me is the possibility of experimenting at a speed that was previously simply impossible. I can try an idea, discard it, modify it, and re-propose it in a very short time. That even changes the way a project is conceived, because it allows exploring many more possibilities before making a final decision.

It also allows me to work on materials that already exist and take them much further: improve images or video, recover information, test lighting, explore different visual solutions, or quickly prepare alternatives for the same proposal. In my case, that has enormous value because I can spend more time on creative decisions and less on processes that previously consumed a large number of hours. The documentation I handle on these tools shows precisely how AI is advancing in restoration, scaling, video treatment, and automation of different production phases.

But I think the most important thing is that we are starting to break the traditional separation between the different phases of a production. Concept, design, 3D, animation, virtual production, editing, and post-production can be increasingly connected. This allows a decision made during visual development to be quickly transferred to the rest of the process and for us to modify a project with much more flexibility.

In the medium term, I imagine a much more hybrid audiovisual production. I don't think traditional processes will disappear or that everything will be generated automatically. I think we will have production environments where generative tools, 3D systems, real-time engines, motion capture, virtual production, and post-production coexist, and where the move from one phase to another is much more fluid.

I also believe that this is going to modify the scale of productions. A small team will be able to visually develop projects that until a few years ago needed much larger structures. And that can be very positive because it will allow certain ideas, which perhaps could not find financing or were not viable due to their complexity, to become prototypes, short films, or even complete productions.

Regarding the future of the sector, I am quite optimistic, although I think it is going to be a period of enormous transformation. Over the next few years, we will see certain ways of working disappear and others appear that we don't even know yet. Some professions will change profoundly and others will merge.

And I think the most interesting thing will be precisely the appearance of new audiovisual languages. Every time a technology changes the available tools, it also changes what we can imagine and the way we can tell it. Cinema, animation, and video games will probably start to share even more processes and languages.

That is why I don't think the future is simply producing the same thing in a faster and cheaper way. I think the real opportunity lies in using this technology to do things we couldn't do before.

We are entering a stage where technology is going to allow imagination to have fewer technical limits. And, personally, I think that is one of the most interesting moments audiovisual creation has experienced.

PO: Do you want to add anything else?

JCA: Yes. I would perhaps add a personal reflection.

I have lived through the transition from a completely analog way of working to digital, then the arrival of 3D, real-time engines, virtual production, and now artificial intelligence. In each of those moments, there has been a sense that something was ending and that the new could destroy the old. Over time, I have learned that tools change much faster than our need to tell stories.

That is why, although I believe we are facing a huge transformation and that many things are going to change, I don't think we should be afraid to imagine what's coming. I think we should try to participate in that transformation.

For me, the most important thing will continue to be the ability to have ideas, develop one's own gaze, and find new ways to tell stories. Tools can change radically and will probably continue to do so, but behind any image that really manages to move, disturb, or surprise, there will still be a human intention.

And perhaps that is what interests me most about this moment: not yet knowing exactly where it's going to lead us.

I think we are living at the beginning of a new stage of audiovisual creation and that we have not yet seen the truly surprising things that artists who grow up and develop their language within it will be capable of doing.