Loading video...

Video Failed to Load

Go Home

Attended this short creative hackathon tonight - using the full stack of creative ai tools to make a short teaser in 3 hours - and won! - script development: ChatGPT Canvas - scene generation: Midjourney - image to video: Hailuo AI (MiniMax) - narrator: ElevenLabs - bgm: Suno -...

swyx's profile picture

swyx

111,857 subscribers

14,542 views • 1 year ago •via X (Twitter)

Science & TechnologyArts
LIVE

Anya Rossi• Live Now

Private livecam show

7 Comments

J. Quintanilla's profile picture
J. Quintanilla1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio They should use liveportrait for lip syncing. To add more human speaking scenes. It would add more depth and emotional connection. 🙂 still pretty tho

William Njau's profile picture
William Njau1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio This is awesome congratulations!!

Lee Gaul's profile picture
Lee Gaul1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio That's amazing - great job! 👏🙌

Keiji Kanazawa's profile picture
Keiji Kanazawa1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio Very cool congratulations!

justboulatbek's profile picture
justboulatbek1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio What editor did you use

William Fitzgerald's profile picture
William Fitzgerald1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio This is amazing

hie sop's profile picture
hie sop1 year ago

@ChatGPTapp @midjourney @Hailuo_AI @elevenlabsio Incredible turnaround in just 3 hours! 🎉 With AI tools like Opencord AI, engaging with your audience can be just as efficient. What strategies do you think could amplify your creative projects even more?

Related Videos

🪐 WORLD CREATORS Generative AI opened the door for everyone to tell their stories without the need for a crew or a big budget. We started slowly with images and saw an enormous interest in tools like Midjourney, DALL-E, or Leonardo. Now, a bit more than a year later, we find ourselves in front of new technologies that are transforming our way of life, how we create, and how we consume content. ChatGPT is rapidly replacing Googling, and all the generative AI tools are replacing all the stock photos and videos, with tools like Runway enabling storytelling for everyone. And we won't take over Hollywood. We will surpass it in ways we can't even imagine right now. We'll be able to create worlds and stories beyond our wildest imagination. Generative AI is enabling creative people to go 1000x on what was possible before. At the core of everything we'll still need human creativity, and we have to understand that AI tools without it will be nothing. Until then, enjoy a short video I've put together to illustrate a small fraction of the worlds we will create soon. What worlds and stories are you excited to create?
2:01

🪐 WORLD CREATORS Generative AI opened the door for everyone to tell their stories without the need for a crew or a big budget. We started slowly with images and saw an enormous interest in tools like Midjourney, DALL-E, or Leonardo. Now, a bit more than a year later, we find ourselves in front of new technologies that are transforming our way of life, how we create, and how we consume content. ChatGPT is rapidly replacing Googling, and all the generative AI tools are replacing all the stock photos and videos, with tools like Runway enabling storytelling for everyone. And we won't take over Hollywood. We will surpass it in ways we can't even imagine right now. We'll be able to create worlds and stories beyond our wildest imagination. Generative AI is enabling creative people to go 1000x on what was possible before. At the core of everything we'll still need human creativity, and we have to understand that AI tools without it will be nothing. Until then, enjoy a short video I've put together to illustrate a small fraction of the worlds we will create soon. What worlds and stories are you excited to create?

Alex Patrascu

59,270 views • 2 years ago

My Latest AI short was made with Seedance 2.0 the model that has been firing up the internet over the past couple of days. I made this in two and half days and it's an original short that is based on HP Lovecraft's work which is now Public Domain (No Copyright infringement here!). If you are not into period romances then bare with it as it gets a more little action packed in the second half! The model is brilliant at both performance and action, you can now make convincing dialogue and action sequences for AI cinema. With this model we have now reached the stage where we can tell any story we want with AI, the tools are capable. This is only 720p at the moment but I suspect it will be upgraded to 1080p very soon. We stand at the threshold of having broadcast quality tools capable of creating anything we can imagine available to everyone, so lets do new an interesting things with it. Thank you to CapCut for whitelisting me and to Dreamina AI AI for giving me access as part of their CPP. Thanks for watching! 👀
3:29

My Latest AI short was made with Seedance 2.0 the model that has been firing up the internet over the past couple of days. I made this in two and half days and it's an original short that is based on HP Lovecraft's work which is now Public Domain (No Copyright infringement here!). If you are not into period romances then bare with it as it gets a more little action packed in the second half! The model is brilliant at both performance and action, you can now make convincing dialogue and action sequences for AI cinema. With this model we have now reached the stage where we can tell any story we want with AI, the tools are capable. This is only 720p at the moment but I suspect it will be upgraded to 1080p very soon. We stand at the threshold of having broadcast quality tools capable of creating anything we can imagine available to everyone, so lets do new an interesting things with it. Thank you to CapCut for whitelisting me and to Dreamina AI AI for giving me access as part of their CPP. Thanks for watching! 👀

Uncanny Harry AI

76,695 views • 4 months ago

A test of pure synthetic performance in a little short called the last dance. All the images were made with Runway Frames, all the dialogue was generated with Google DeepMind Veo2 in , the dancing and additional footage was generated with Hailuo AI (MiniMax) and the singers lip-synch shot was done with Higgsfield AI 🧩 speak. Music made with Suno using my Uncanny Harriet persona. Took a day and a half, script to final cut. Let me know your thoughts. Next up will be a Act Two powered short.👀
1:48

A test of pure synthetic performance in a little short called the last dance. All the images were made with Runway Frames, all the dialogue was generated with Google DeepMind Veo2 in , the dancing and additional footage was generated with Hailuo AI (MiniMax) and the singers lip-synch shot was done with Higgsfield AI 🧩 speak. Music made with Suno using my Uncanny Harriet persona. Took a day and a half, script to final cut. Let me know your thoughts. Next up will be a Act Two powered short.👀

Uncanny Harry AI

15,141 views • 11 months ago

$LUNC just pumped over 100% in a short window of time. What are we watching for here in May? What are the keys for Terra Luna Classic to not sell all the way off again? We had the pump late in 2025 but it was short lived. This seems to be a little different...
12:39

$LUNC just pumped over 100% in a short window of time. What are we watching for here in May? What are the keys for Terra Luna Classic to not sell all the way off again? We had the pump late in 2025 but it was short lived. This seems to be a little different...

Zach Humphries

30,492 views • 1 month ago

Pixar but make it AI? Using only AI tools we made a full Pixar Style Short. And it was so easy we decided to share the sauce 👀
0:25

Pixar but make it AI? Using only AI tools we made a full Pixar Style Short. And it was so easy we decided to share the sauce 👀

HeyGen

14,793 views • 10 months ago

Two weeks in Japan. Hundreds of photos. One creative rabbit hole I couldn’t resist going down. Last year, I created a song as an experiment. I wanted to blend Japanese and English lyrics and see what kind of mood it would create. It turned into something atmospheric and different from anything I’d done before. Then my wife and I spent two incredible weeks in Japan late last year, and the experience stuck with me. Seeing the temples, shrines, and local shops while my wife and I wandered around Kyoto left a lasting impression. When I got back, I realized that the song needed a visual story. So I decided to build a full music video around it. I started by fleshing out the concept and writing a shot list like a real production. Then the fun began. What’s interesting is that many of the locations you see in the video actually started as photos I took while my wife and I wandered around Kyoto. Those images became the foundation for the environments that were later generated and brought to life with AI. It was a fascinating, creative process. Part music creation, part photography, part storytelling, and part AI experimentation. Tools used in the process: Nano Banana Pro (Google Flow) – for image generation Midjourney (Midjourney) – for additional image creation Google VEO3 (Google Flow) – for video generation Kling 3.0 (Kling AI) – for video generation Final Cut Pro (Apple) – for editing SUNO (Suno) – for song generation Amazing how far the creative toolset has come. If you have an idea in your head, you can now actually build it! Take a minute to watch Rain + Light (雨と光) and tell me what stood out to you. Would love to hear your feedback.
4:02

Two weeks in Japan. Hundreds of photos. One creative rabbit hole I couldn’t resist going down. Last year, I created a song as an experiment. I wanted to blend Japanese and English lyrics and see what kind of mood it would create. It turned into something atmospheric and different from anything I’d done before. Then my wife and I spent two incredible weeks in Japan late last year, and the experience stuck with me. Seeing the temples, shrines, and local shops while my wife and I wandered around Kyoto left a lasting impression. When I got back, I realized that the song needed a visual story. So I decided to build a full music video around it. I started by fleshing out the concept and writing a shot list like a real production. Then the fun began. What’s interesting is that many of the locations you see in the video actually started as photos I took while my wife and I wandered around Kyoto. Those images became the foundation for the environments that were later generated and brought to life with AI. It was a fascinating, creative process. Part music creation, part photography, part storytelling, and part AI experimentation. Tools used in the process: Nano Banana Pro (Google Flow) – for image generation Midjourney (Midjourney) – for additional image creation Google VEO3 (Google Flow) – for video generation Kling 3.0 (Kling AI) – for video generation Final Cut Pro (Apple) – for editing SUNO (Suno) – for song generation Amazing how far the creative toolset has come. If you have an idea in your head, you can now actually build it! Take a minute to watch Rain + Light (雨と光) and tell me what stood out to you. Would love to hear your feedback.

Chip – onthechain.io

12,993 views • 3 months ago

Back in 1978, when I was just 23, I traveled from Istanbul to Kathmandu with my best friend, Gene. It was quite an adventure for a couple of kids just out of college. There was no way of connecting with loved ones. We didn’t know where the end of our trail was. There were no guidebooks. For us, it was a venture into uncharted territory. It was a journey of discovery, to question our Western values and help us better understand the world. Along the way, we made friends in Tehran, got lost in Lahore, got high for the first time in Herat, battled leeches in Pokhara, and much more. We were free and earnest, but the trip helped us build a better empathy for cultures and humility for seeing what a small speck we were in this world. Almost 50 years later, I still pack along that curiosity whenever and wherever I travel. What drove me to write a 60,000-word journal along the way is beyond me…but with that journal as the basis for my new book, “On the Hippie Trail: Istanbul to Kathmandu and the Making of a Travel Writer,” you’re invited to join me on what was far and away, the trip of my life.
1:30

Back in 1978, when I was just 23, I traveled from Istanbul to Kathmandu with my best friend, Gene. It was quite an adventure for a couple of kids just out of college. There was no way of connecting with loved ones. We didn’t know where the end of our trail was. There were no guidebooks. For us, it was a venture into uncharted territory. It was a journey of discovery, to question our Western values and help us better understand the world. Along the way, we made friends in Tehran, got lost in Lahore, got high for the first time in Herat, battled leeches in Pokhara, and much more. We were free and earnest, but the trip helped us build a better empathy for cultures and humility for seeing what a small speck we were in this world. Almost 50 years later, I still pack along that curiosity whenever and wherever I travel. What drove me to write a 60,000-word journal along the way is beyond me…but with that journal as the basis for my new book, “On the Hippie Trail: Istanbul to Kathmandu and the Making of a Travel Writer,” you’re invited to join me on what was far and away, the trip of my life.

Rick Steves

73,173 views • 1 year ago

🎬Midjourney + Runway + Hailuo AI + Udio: "This Christmas" (AI music video) It's such a magical time of year! In December, I get the chance to spend quality time with my family, cook something creative, and share the joy of giving through thoughtful gifts. No matter what you celebrate, or if you celebrate at all, I wish you a wonderful time with your loved ones, a chance to relax, and all the best for the holidays and the year ahead 🩶 Images: Midjourney 6.1 Video: Gen-3 and Hailuo AI (MiniMax) Music: Udio v 1.5 Editing: CapCut
0:32

🎬Midjourney + Runway + Hailuo AI + Udio: "This Christmas" (AI music video) It's such a magical time of year! In December, I get the chance to spend quality time with my family, cook something creative, and share the joy of giving through thoughtful gifts. No matter what you celebrate, or if you celebrate at all, I wish you a wonderful time with your loved ones, a chance to relax, and all the best for the holidays and the year ahead 🩶 Images: Midjourney 6.1 Video: Gen-3 and Hailuo AI (MiniMax) Music: Udio v 1.5 Editing: CapCut

Everett World

14,314 views • 1 year ago

Isabelle Boemeke isabelle 🪐 on the pre-Hiroshima moment we’re in with AI. "The United States rushes to build the bomb, and up until that point there was a mix of excitement and fear about nuclear. I think it's similar to what we feel about AI at this moment. We are in that moment with AI where we can see both scenarios in our minds, right? It could be incredible. We could cure all these diseases, we could solve all these complex problems, but we can also all die. And it was a very similar thing, until the bombs were dropped in Hiroshima and Nagasaki and all of that potential was cemented in one image, which was of a mushroom cloud."
3:13

Isabelle Boemeke isabelle 🪐 on the pre-Hiroshima moment we’re in with AI. "The United States rushes to build the bomb, and up until that point there was a mix of excitement and fear about nuclear. I think it's similar to what we feel about AI at this moment. We are in that moment with AI where we can see both scenarios in our minds, right? It could be incredible. We could cure all these diseases, we could solve all these complex problems, but we can also all die. And it was a very similar thing, until the bombs were dropped in Hiroshima and Nagasaki and all of that potential was cemented in one image, which was of a mushroom cloud."

Sabrina Halper

41,314 views • 4 months ago

Traditional media is DEAD. They just don't know it yet.. Everything you see in this Ad was 100% created with AI. Yes, really.. And it only took me about an hour. - the storyboard (Nano Banana) - the music (Suno) - the animations (Kling) - the voiceover (Elevenlabs) Creative teams are now able to move at the speed of thought. The problem is a lot of the tools are still fragmented. But there's something magical that happens when you piece everything together. I tried every tool out there under the sun that claims to be a full stack studio but they all felt short. Had to build my own (screenshot in comments); If I can do this in under an hour imagine what entire creative and media teams can do. And now that I have your attention: - If you want $2000 off your SOC 2 before end of year, just reach out and mention you saw this video.
0:43

Traditional media is DEAD. They just don't know it yet.. Everything you see in this Ad was 100% created with AI. Yes, really.. And it only took me about an hour. - the storyboard (Nano Banana) - the music (Suno) - the animations (Kling) - the voiceover (Elevenlabs) Creative teams are now able to move at the speed of thought. The problem is a lot of the tools are still fragmented. But there's something magical that happens when you piece everything together. I tried every tool out there under the sun that claims to be a full stack studio but they all felt short. Had to build my own (screenshot in comments); If I can do this in under an hour imagine what entire creative and media teams can do. And now that I have your attention: - If you want $2000 off your SOC 2 before end of year, just reach out and mention you saw this video.

Claudio Fuentes

11,644 views • 6 months ago

What an unforgettable day. 🏆✨ After 9 years of waiting, we were honored to finally bring 🌼 Marc-André Fleury 🌸 to the fans for a public event like this—and grateful that we were the ones able to make it happen. Thank you to all the fans who joined us for the event. Throughout the signing, 9️⃣0️⃣0️⃣+ fans came through the line 🤯. We’re truly grateful for the patience and support shown by everyone who waited to be part of this moment, and we hope it was well worth it. Vegas fans showed up in a big way. The love and support for Fleury was loud and clear—he’s still our guy, and always will be. A huge thank you to our staff and helpers for the long hours, teamwork, and execution it took to make this day possible for the fans. And thank you to our partners at Fanatics for working with us to help bring this together. More highlights to come!!
0:28

What an unforgettable day. 🏆✨ After 9 years of waiting, we were honored to finally bring 🌼 Marc-André Fleury 🌸 to the fans for a public event like this—and grateful that we were the ones able to make it happen. Thank you to all the fans who joined us for the event. Throughout the signing, 9️⃣0️⃣0️⃣+ fans came through the line 🤯. We’re truly grateful for the patience and support shown by everyone who waited to be part of this moment, and we hope it was well worth it. Vegas fans showed up in a big way. The love and support for Fleury was loud and clear—he’s still our guy, and always will be. A huge thank you to our staff and helpers for the long hours, teamwork, and execution it took to make this day possible for the fans. And thank you to our partners at Fanatics for working with us to help bring this together. More highlights to come!!

Inscriptagraphs Memorabilia

11,276 views • 4 months ago

Dana White on how Paramount+ deal came together: We were in negotiations for awhile with everybody and it was looking like we were going to have to chop up the content like the NFL does...and then literally in the 23rd hour Paramount came in and said, 'We want it all and here's what we'll pay for it.'
0:47

Dana White on how Paramount+ deal came together: We were in negotiations for awhile with everybody and it was looking like we were going to have to chop up the content like the NFL does...and then literally in the 23rd hour Paramount came in and said, 'We want it all and here's what we'll pay for it.'

Jed I. Goodman ©

29,273 views • 1 month ago

"But what is a mental image? Not for the last time, I got caught up, when I was in graduate school, in a raging controversy called the imagery debate. And this was a debate over the format of mental imagery. Now, everyone reports the experience of a mental picture, and that’s the way we describe it in English. But, of course, there isn’t a real picture in the brain. It isn’t as if there’s a little man sitting in a theater who’s looking at a screen. The behaviorists were right about this. How do we make sense of what’s going on in people’s heads when they say they have a mental picture? The easiest way to make sense of it is to use the concept from computer science of an image file—basically, an array of pixels, as we would now call them. And my graduate advisor, Stephen Kosslyn, came up with what at the time was a revolutionary theory: that images were like image files in a computer." I'll be saying more about the workings of the human mind in February 2026 in Australia and New Zealand. Thinkable
1:02

"But what is a mental image? Not for the last time, I got caught up, when I was in graduate school, in a raging controversy called the imagery debate. And this was a debate over the format of mental imagery. Now, everyone reports the experience of a mental picture, and that’s the way we describe it in English. But, of course, there isn’t a real picture in the brain. It isn’t as if there’s a little man sitting in a theater who’s looking at a screen. The behaviorists were right about this. How do we make sense of what’s going on in people’s heads when they say they have a mental picture? The easiest way to make sense of it is to use the concept from computer science of an image file—basically, an array of pixels, as we would now call them. And my graduate advisor, Stephen Kosslyn, came up with what at the time was a revolutionary theory: that images were like image files in a computer." I'll be saying more about the workings of the human mind in February 2026 in Australia and New Zealand. Thinkable

Steven Pinker

113,593 views • 7 months ago

"In 90 days... we've had 1.2 million of the 3 million people at the department use some form of AI. That number was 80,000 before I started." Emil Michael on reshaping the Department of War's priorities and going all in on AI: "When I took the role in May... we had 14 critical priority areas in this role... they hadn't changed in nearly a decade." "Who can remember 14 things when you're trying to motivate a workforce?" "We got them down to six... they were places where I thought we had the greatest opportunity for change and for growth and impact on our combat power and for our industrial base." "Applied AI was number one. So then we moved the chief digital and AI office into my group, and we were able to run extremely fast with that... we're way behind in AI at the department, and we know it's penetrating the rest of the world so dramatically, so quickly." "Our adversaries were also using it... they want to use computers to eliminate human decision making. We want to enhance human decision making." Under Secretary of War Emil Michael Department of War CTO David Ulevitch 🇺🇸
1:42

"In 90 days... we've had 1.2 million of the 3 million people at the department use some form of AI. That number was 80,000 before I started." Emil Michael on reshaping the Department of War's priorities and going all in on AI: "When I took the role in May... we had 14 critical priority areas in this role... they hadn't changed in nearly a decade." "Who can remember 14 things when you're trying to motivate a workforce?" "We got them down to six... they were places where I thought we had the greatest opportunity for change and for growth and impact on our combat power and for our industrial base." "Applied AI was number one. So then we moved the chief digital and AI office into my group, and we were able to run extremely fast with that... we're way behind in AI at the department, and we know it's penetrating the rest of the world so dramatically, so quickly." "Our adversaries were also using it... they want to use computers to eliminate human decision making. We want to enhance human decision making." Under Secretary of War Emil Michael Department of War CTO David Ulevitch 🇺🇸

a16z

36,133 views • 3 months ago

Hailuo AI: Transforming Your Ideas into Movie Clips I was blown away to hear that the team behind Hailuo AI-MiniMax Hub was only six people! AI is truly revolutionising the way we create. I used to doubt Text to Video could be useful for filmmaking, but this model changed my mind. The trick is to prompt like a film director, giving instructions on acting and camera with natural language. Check out some the prompts I used: 🧵
0:45

Hailuo AI: Transforming Your Ideas into Movie Clips I was blown away to hear that the team behind Hailuo AI-MiniMax Hub was only six people! AI is truly revolutionising the way we create. I used to doubt Text to Video could be useful for filmmaking, but this model changed my mind. The trick is to prompt like a film director, giving instructions on acting and camera with natural language. Check out some the prompts I used: 🧵

el.cine

134,057 views • 1 year ago

She smiled under the daylight, as if the world was still whole. But when night came, silence brought back the faces she missed. Traces of Life: a story about warmth, loss, and the moments that never truly leave us. Sometimes, we don’t move on… we just learn to live with what remains. Brought to life with: Image: ImagineArt 1.0 ImagineArt Video: Hailuo AI (MiniMax) 2 Pro in ImagineArt Upscaled: Astra Topaz Labs Editing & layering: CapCut SFX: ElevenLabs This music video was submitted for the AI Music Video Competition at Chroma Awards #chromaawards #imagineart1.0
2:04

She smiled under the daylight, as if the world was still whole. But when night came, silence brought back the faces she missed. Traces of Life: a story about warmth, loss, and the moments that never truly leave us. Sometimes, we don’t move on… we just learn to live with what remains. Brought to life with: Image: ImagineArt 1.0 ImagineArt Video: Hailuo AI (MiniMax) 2 Pro in ImagineArt Upscaled: Astra Topaz Labs Editing & layering: CapCut SFX: ElevenLabs This music video was submitted for the AI Music Video Competition at Chroma Awards #chromaawards #imagineart1.0

DStudioproject

11,529 views • 8 months ago

Richard and I were invited to a Halloween party just after we landed in LA but we had no outfits - so we had to get creative 🤣 the result was a literal embodiment of ‘Murder On The Dancefloor’!! Show #1 of the North American tour kicks off tonight in LA and I can’t wait!💃
0:32

Richard and I were invited to a Halloween party just after we landed in LA but we had no outfits - so we had to get creative 🤣 the result was a literal embodiment of ‘Murder On The Dancefloor’!! Show #1 of the North American tour kicks off tonight in LA and I can’t wait!💃

Sophie Ellis-Bextor

66,187 views • 8 months ago

Some people don't know this, but we also make music. "Would You?" - by Dorphism All the visuals were made on and animated on Kling AI The song was recorded in real life and remixed with Suno
2:00

Some people don't know this, but we also make music. "Would You?" - by Dorphism All the visuals were made on and animated on Kling AI The song was recorded in real life and remixed with Suno

The Dor Brothers

40,316 views • 4 months ago

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:
0:23

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:

TITLES

2,745,836 views • 2 months ago

We are hiring creative strategists. If you’re excited about AI video and ads, this role is for you. With AI you can make anything. But making something worth watching requires a human. That’s why we’re building a super-team of creative strategists. You will: - Work with the fastest growing and largest AI brands - Be paid to learn at the frontier of AI - Work with the top AI marketers, filmmakers, engineers, and creators - Ship more ads per day than others do in a month
1:00

We are hiring creative strategists. If you’re excited about AI video and ads, this role is for you. With AI you can make anything. But making something worth watching requires a human. That’s why we’re building a super-team of creative strategists. You will: - Work with the fastest growing and largest AI brands - Be paid to learn at the frontier of AI - Work with the top AI marketers, filmmakers, engineers, and creators - Ship more ads per day than others do in a month

Rahul Bhardwaj

45,748 views • 20 days ago