This project was a special one. Sania Bhatia (Tisch ’26) and I created a music video for an artist from NYU Clive Davis, incorporating generative AI into our creative process.
As our final project for the first Generative Filmmaking in the Age of Hypercinema class, taught by NYC artist Gabriel Barcia Colombo, it brought together everything we had been experimenting with throughout the semester, from generative AI models and prompt-based workflows to traditional filmmaking and immersive design tools.
View the project below, along with our testimonies about the process, and on generative AI as artists.
my role
VFX Generator, Assistant filmmaker
LOCATION
New York, New York
tools
DaVinci Resolve, Generative AI tools used: MidJourney, Flora Fauna, Runway 2.0, Google Gemini, ChatGPT
sPECIAL THANKS
Sania Bhatia (NYU Tisch), Gabe Barcia-Colombo (Instructor ITP), Harry Winer (Instructor, NYU Tisch)
04
generative ai MUSIC VIDEO
MsUse
November 2025 - December 2025
Next project
This project was a special one. Sania Bhatia (Tisch ’26) and I were paired to create a music video for an artist from Clive Davis, NYU’s music school, incorporating generative AI into our creative process.
Created as our final project for First-Time Generative Filmmaking in the Age of Hypercinema, taught by NYC artist Gabriel Barcia Colombo, the project brought together everything we had been experimenting with throughout the semester, everything from generative AI models and prompt-based workflows to traditional filmmaking and immersive design tools.
View the project below as well as our testimonies to the process and our thoughts on generative AI as artists.
This project was a special one. Sania Bhatia (Tisch ’26) and I created a music video for an artist from NYU Clive Davis, incorporating generative AI into our creative process.
As our final project for the first Generative Filmmaking in the Age of Hypercinema class, taught by NYC artist Gabriel Barcia Colombo, it brought together everything we had been experimenting with throughout the semester, from generative AI models and prompt-based workflows to traditional filmmaking and immersive design tools.
View the project below, along with our testimonies about the process, and on generative AI as artists.
This project was a special one. Sania Bhatia (Tisch ’26) and I created a music video for an artist from NYU Clive Davis, incorporating generative AI into our creative process.
As our final project for the first Generative Filmmaking in the Age of Hypercinema class, taught by NYC artist Gabriel Barcia Colombo, it brought together everything we had been experimenting with throughout the semester, from generative AI models and prompt-based workflows to traditional filmmaking and immersive design tools.
View the project below, along with our testimonies about the process, and on generative AI as artists.
my role
VFX Generator, Assistant filmmaker
LOCATION
New York, New York
tools
DaVinci Resolve, Generative AI tools used: MidJourney, Flora Fauna, Runway 2.0, Google Gemini, ChatGPT
sPECIAL THANKS
Sania Bhatia (NYU Tisch), Gabe Barcia-Colombo (Instructor ITP)
Sania Bhatia (NYU Tisch), Gabe Barcia-Colombo (Instructor ITP), Harry Winer (Instructor, NYU Tisch)
Next project
© 2026 Lisa Lei. All rights reserved.
© 2026 Lisa Lei. All rights reserved.
Next project
© 2026 Lisa Lei. All rights reserved.
In my Interactive Media Arts program, AI experimentation is widely accepted, though opinions vary. With my visual design background, I’ve typically used AI for early ideation and prototyping. For this music video, that role shifted: we developed the storyboard first, then used AI to enhance footage we shot ourselves.
As the project progressed, my sense of what was executable expanded.
In my Interactive Media Arts program, AI experimentation is widely accepted, though opinions vary. With my visual design background, I’ve typically used AI for early ideation and prototyping. For this music video, that role shifted: we developed the storyboard first, then used AI to enhance footage we shot ourselves.
As the project progressed, my sense of what was executable expanded.
LOOKING FOR THE COMPLETE PICTURE?
I’m a designer who loves to talk through ideas and visuals. I believe the best way to understand my process is through conversation, so let me walk you through the full process and prototype.
LOOKING FOR THE COMPLETE PICTURE?
I’m a designer who loves to talk through ideas and visuals. I believe the best way to understand my process is through conversation, so let me walk you through the full process and prototype.
I’m a designer who loves to talk through ideas and visuals. I believe the best way to understand my process is through conversation, so let me walk you through the full process and prototype.
LOOKING FOR THE COMPLETE PICTURE?
Seeing how much effort goes into even the shortest scenes, and how grueling the editing process was, particularly when integrating AI and hiding its mistakes - made this one of the highlights of my undergraduate experience.
MsUse may appear highly machine-generated, but it involved as much, if not more, human conceptualization and effort than any other project I’ve made at NYU so far.
MsUse was screened twice at Clive Davis Theatre, NYC, and at NYU Tisch Screening Theatre, NYC.
Thank you Harry Winer and Gabe BC for organizing and all your support.
MsUse was screened twice at Clive Davis Theatre, NYC, and at NYU Tisch Screening Theatre, NYC.
Thank you Harry Winer and Gabe BC for organizing and all your support.
MsUse was screened twice at Clive Davis Theatre, NYC, and at NYU Tisch Screening Theatre, NYC.
Thank you Harry Winer and Gabe BC for organizing and all your support.
Seeing how much effort goes into even the shortest scenes, and how grueling the editing process was, particularly when integrating AI and hiding its mistakes - made this one of the highlights of my undergraduate experience.
MsUse may appear highly machine-generated, but it involved as much, if not more, human conceptualization and effort than any other project I’ve made at NYU so far.
Seeing how much effort goes into even the shortest scenes, and how grueling the editing process was, particularly when integrating AI and hiding its mistakes - made this one of the highlights of my undergraduate experience.
MsUse may appear highly machine-generated, but it involved as much, if not more, human conceptualization and effort than any other project I’ve made at NYU so far.
"I don’t use AI in my filmmaking, other than in this video. (…) But ethically, through attempting to make something with a tool I was previously afraid of, I’ve eradicated some fears I had around the extinction of artistic humanity (…).
We could make any face sing the song, from candy bars to nickels. The wrong people might misuse this ability but the least we can do is have fun. AI is the largest mirror we’ve held up to us technologically, yet it's a black box. It learns from us, but we also learn from other artists. Does that also make it a creator? Or a co-creator? Does it need us?
Sania Bhatia NYU TISCH 26'
"I don’t use AI in my filmmaking, other than in this video. (…) But ethically, through attempting to make something with a tool I was previously afraid of, I’ve eradicated some fears I had around the extinction of artistic humanity (…).
We could make any face sing the song, from candy bars to nickels. The wrong people might misuse this ability but the least we can do is have fun. AI is the largest mirror we’ve held up to us technologically, yet it's a black box. It learns from us, but we also learn from other artists. Does that also make it a creator? Or a co-creator? Does it need us?
Sania Bhatia NYU TISCH 26'
"I don’t use AI in my filmmaking, other than in this video. (…) But ethically, through attempting to make something with a tool I was previously afraid of, I’ve eradicated some fears I had around the extinction of artistic humanity (…).
We could make any face sing the song, from candy bars to nickels. The wrong people might misuse this ability but the least we can do is have fun. AI is the largest mirror we’ve held up to us technologically, yet it's a black box. It learns from us, but we also learn from other artists. Does that also make it a creator? Or a co-creator? Does it need us?
Sania Bhatia NYU TISCH 26'
BTS AND STILLS
BTS AND STILLS
ChatGPT
RunwayChatGPT
A workflow I discovered with the help of an ITP student was using a multi-tiered prompting process. This is where the pool scene truly shined. At first, the AI videos we were getting either flattened his face onto the silhouette of the ball or didn’t change it at all.
The workflow was to first ask ChatGPT to generate a text prompt specifically for Google Gemini to create the still photo. Once we had a 3D-looking photo, we asked ChatGPT to generate a second video prompt directly for Midjourney that was able to bring the still photo to life. The result took a week and involved a lot of creative solutions, but it was so worth it.
inside the work
ChatGPTRunwayChatGPTA workflow I discovered with the help of an ITP student was using a multi-tiered prompting process. This is where the pool scene truly shined. At first, the AI videos we were getting either flattened his face onto the silhouette of the ball or didn’t change it at all.
The workflow was to first ask ChatGPT to generate a text prompt specifically for Google Gemini to create the still photo. Once we had a 3D-looking photo, we asked ChatGPT to generate a second video prompt directly for Midjourney that was able to bring the still photo to life. The result took a week and involved a lot of creative solutions, but it was so worth it.
inside the work
ChatGPTRunwayChatGPTA workflow I discovered with the help of an ITP student was using a multi-tiered prompting process. This is where the pool scene truly shined. At first, the AI videos we were getting either flattened his face onto the silhouette of the ball or didn’t change it at all.
The workflow was to first ask ChatGPT to generate a text prompt specifically for Google Gemini to create the still photo. Once we had a 3D-looking photo, we asked ChatGPT to generate a second video prompt directly for Midjourney that was able to bring the still photo to life. The result took a week and involved a lot of creative solutions, but it was so worth it.
inside the work
BTS AND STILLS
Preview of MsUse
Preview of MsUse
Preview of MsUse
