Nicolas Neubert's banner

Nicolas Neubert

@iamneubert • 63,339 subscribers

✦ Senior Manager, Technical Artists at @runwayml. ✦ Chief Gaming Officer at Runway Games ✦ Work recognized by Forbes, The New York Times, Bloomberg & CNN.

Shorts

Me next Monday.

Me next Monday.

4,336,311 просмотров

Tomorrow, we explore a new world.

Tomorrow, we explore a new world.

387,595 просмотров

So... I guess it's a ReAl 3D MoDeL now. (Unfortunately, the pipeline now takes 2 clicks and ~5 minutes to create a 3D character.)

So... I guess it's a ReAl 3D MoDeL now. (Unfortunately, the pipeline now takes 2 clicks and ~5 minutes to create a 3D character.)

75,592 просмотров

This is exactly how it felt to play on that carpet as a child. Made by the super talented David Hult.

This is exactly how it felt to play on that carpet as a child. Made by the super talented David Hult.

97,531 просмотров

Prompt: Highly intense scene of the hunter sneaking through the forest and getting ambushed by a large furry creature Made using Runway's Multi-Shot App

Prompt: Highly intense scene of the hunter sneaking through the forest and getting ambushed by a large furry creature Made using Runway's Multi-Shot App

43,163 просмотров

Warden Concept - Defends on sight.

Warden Concept - Defends on sight.

45,170 просмотров

Made quicker than I could finish my first cappuccino of the day.

Made quicker than I could finish my first cappuccino of the day.

46,487 просмотров

🧪 Female Portraits in GEN-3 Alpha I think I've finally cracked a prompt structure applicable to all female portrait styles in I2V to give them natural movement! Prompt: static camera, fast natural movement, dynamic motion, fashion portrait, she looks at us with love, cheeky eyes and lips, blinking eyes. ✨ Pro Tip: If your seeing color shifts or are working with lower contrast input images, add "muted colors, low contrast" to the beginning of the prompt.

🧪 Female Portraits in GEN-3 Alpha I think I've finally cracked a prompt structure applicable to all female portrait styles in I2V to give them natural movement! Prompt: static camera, fast natural movement, dynamic motion, fashion portrait, she looks at us with love, cheeky eyes and lips, blinking eyes. ✨ Pro Tip: If your seeing color shifts or are working with lower contrast input images, add "muted colors, low contrast" to the beginning of the prompt.

97,719 просмотров

April 2025 vs April 2026 Wild that people still believe AI will never look as good as CGI. If an aspiring filmmaker submitted this as a CGI scene, they'd get hired instantly.

April 2025 vs April 2026 Wild that people still believe AI will never look as good as CGI. If an aspiring filmmaker submitted this as a CGI scene, they'd get hired instantly.

27,259 просмотров

Runway is the best place to bring any idea you’ve ever imagined to life.

Runway is the best place to bring any idea you’ve ever imagined to life.

25,549 просмотров

With Runway Aleph, Sydney Sweeney can wear her great jeans in her favorite color.

With Runway Aleph, Sydney Sweeney can wear her great jeans in her favorite color.

45,774 просмотров

Not having quality degradation across a generation is one of my favorite new aspects of I2V in GEN-3 Alpha. Together with precise prompting - chef's kiss! Prompt: static camera, fast natural movement, dynamic motion, fashion portrait, she looks at us with love, cheeky eyes and lips, blinking eyes

Not having quality degradation across a generation is one of my favorite new aspects of I2V in GEN-3 Alpha. Together with precise prompting - chef's kiss! Prompt: static camera, fast natural movement, dynamic motion, fashion portrait, she looks at us with love, cheeky eyes and lips, blinking eyes

58,001 просмотров

UFOs spotted in Ibiza

UFOs spotted in Ibiza

11,856 просмотров

🏛️ Returning the The Temple of Dendur to the desert. Videos like this can now be generated in two sentences by using Aleph and recorded footage from your phone. 1️⃣ Place this temple in a rocky desert, remove all the people, change the weather to a heavy sandstorm, and add a strong orange tint. 2️⃣ Create two additional videos, with the first showing an orbiting shot of the entrance of the temple and the second showing a close-up of hieroglyphs carved into the interior walls.

🏛️ Returning the The Temple of Dendur to the desert. Videos like this can now be generated in two sentences by using Aleph and recorded footage from your phone. 1️⃣ Place this temple in a rocky desert, remove all the people, change the weather to a heavy sandstorm, and add a strong orange tint. 2️⃣ Create two additional videos, with the first showing an orbiting shot of the entrance of the temple and the second showing a close-up of hieroglyphs carved into the interior walls.

35,228 просмотров

🧪 My GEN-3 Prompting Process I get a lot of questions on how I find my prompts when using Image-2-Video in Runway. Here is a quick breakdown of the general thought process. If you have any further questions, let's chat in the comments below. 1️⃣ I always start by doing 3x generations without any prompts and additional settings. 2️⃣ I analyze those 3x generations and identify patterns. What did the model always do well, where did it fail. 3️⃣ I then use prompting and the different controllability features to eliminate where the model struggled on its own. --- General Tips --- *️⃣ There are some tokens which work universally. "Muted colors, low contrast" are great to preserve the colors of the original input image. "Static camera, natural movement" works fantastically to get cinematic shots. *️⃣ My I2V prompts are on the shorter side. It's usually a sentence describing the scene and then individual modifiers like the ones mentioned above to fix certain camera/lighting/movement artifacts. *️⃣ Start small and prompt engineer in steps. This is very much an iterative process which rewards you for understanding model behavior and knowing how to craft a visual architecture with words. --- Disclaimer --- Please note that this approach is more suitable for a professional workflow. Therefore, I recommend it for users on the unlimited plan who don't need to worry about credits.

🧪 My GEN-3 Prompting Process I get a lot of questions on how I find my prompts when using Image-2-Video in Runway. Here is a quick breakdown of the general thought process. If you have any further questions, let's chat in the comments below. 1️⃣ I always start by doing 3x generations without any prompts and additional settings. 2️⃣ I analyze those 3x generations and identify patterns. What did the model always do well, where did it fail. 3️⃣ I then use prompting and the different controllability features to eliminate where the model struggled on its own. --- General Tips --- ️⃣ There are some tokens which work universally. "Muted colors, low contrast" are great to preserve the colors of the original input image. "Static camera, natural movement" works fantastically to get cinematic shots. ️⃣ My I2V prompts are on the shorter side. It's usually a sentence describing the scene and then individual modifiers like the ones mentioned above to fix certain camera/lighting/movement artifacts. *️⃣ Start small and prompt engineer in steps. This is very much an iterative process which rewards you for understanding model behavior and knowing how to craft a visual architecture with words. --- Disclaimer --- Please note that this approach is more suitable for a professional workflow. Therefore, I recommend it for users on the unlimited plan who don't need to worry about credits.

46,240 просмотров

Me and the squad moving through the city.

Me and the squad moving through the city.

16,420 просмотров

Reminder that you can do this scene in 2 minutes, on your phone, using the Runway app. Think about that for a second.

Reminder that you can do this scene in 2 minutes, on your phone, using the Runway app. Think about that for a second.

34,008 просмотров

✨ New Feature: Runway Motion Slider I have been waiting for this feature for a long time! We can finally control how much movement Runway adds to our images. This feature will save me a lot of iterations in the future! I'm especially excited for the lower motion values!

✨ New Feature: Runway Motion Slider I have been waiting for this feature for a long time! We can finally control how much movement Runway adds to our images. This feature will save me a lot of iterations in the future! I'm especially excited for the lower motion values!

51,788 просмотров

This is too much fun.

This is too much fun.

10,844 просмотров

Tomorrow -- Tomorrow feels like a good day to drop something.

Tomorrow -- Tomorrow feels like a good day to drop something.

20,914 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

When AI Bros enter the chat.

When AI Bros enter the chat.

Nicolas Neubert

8,117,288 просмотров • 29 дней назад

This ad cost $9 and took 10 minutes to make.

This ad cost $9 and took 10 minutes to make.

Nicolas Neubert

10,957,451 просмотров • 1 месяц назад

BREAKING: Why Elon needs good weather for the Tesla Roadster demo.

BREAKING: Why Elon needs good weather for the Tesla Roadster demo.

Nicolas Neubert

695,663 просмотров • 18 дней назад

Simulating gameplay cause and effects is a huge unlock for dev-studios across the industry.

Simulating gameplay cause and effects is a huge unlock for dev-studios across the industry.

Nicolas Neubert

137,543 просмотров • 26 дней назад

Make mistakes. Some shots that didn’t end up going anywhere.

Make mistakes. Some shots that didn’t end up going anywhere.

Nicolas Neubert

75,006 просмотров • 28 дней назад

Welcome to a new frontier of generative storytelling. Gen-4 is available now.

Welcome to a new frontier of generative storytelling. Gen-4 is available now.

Nicolas Neubert

1,292,732 просмотров • 1 год назад

Introducing Whisper Thunder aka Gen-4.5. Today, we are excited to share our new frontier model. Gen-4.5 was built by a team that fits onto two school buses and decided to take on the largest companies in the world. We are David and we’ve brought one hell of a slingshot.

Introducing Whisper Thunder aka Gen-4.5. Today, we are excited to share our new frontier model. Gen-4.5 was built by a team that fits onto two school buses and decided to take on the largest companies in the world. We are David and we’ve brought one hell of a slingshot.

Nicolas Neubert

703,161 просмотров • 10 месяцев назад

Full Breakdown: How I Created a Viral Ad This will be a very long post as I will provide you with the exact way I achieved the original ad, as well as a prompt that get's you straight to the result in case you want to speed-run it. How I created the original: I made the ad collaborating with an agent. You can do this on the Runway platform, via the ChatGPT Runway Plugin or using Runway MCP. I asked the Agent the following: "Can you make a 30 second seedance 2.5 optimised prompt where the story is someone on vacation (beach/zipline/kayaking/hotairballoon/etc.) gets texted by his boss for one final change ASAP. They then look slightly concerned followed by the camera zooming out to reveal a vast landscape. Make sure to end on a super wide shot so that taglines can be added." It ran some thoughts by me, and as I genuinely didn't expect this to blow up, I just blindly let it do its thing and told the agent to start the video generation. The result is the one that you saw a few days ago. Keep in mind that results may vary, as many agents create personalized profiles of you based on their previous conversations. Once you have a prompt/result you like, you can go back to the agent and ask something like the following to get more variations: "What are other funny situations we can do that use the exact same structure?" ------------------------------ You can also skip all that, as I am sharing the exact prompt I used below. I used Seedance 2.5 set to 30 sec duration for my ads. 720p gives you that $9 ad, however you can also run it at 1080p for a more final production spec asset. You can also give the prompt to an LLM and ask it to make new narrative scenarios, using the exact same prompt structure. 🧵 Prompt is in the thread below! 🧵 Thank you for all the love on the ad. I've already seen a bunch of spin-offs, and can't wait to see even more.

Full Breakdown: How I Created a Viral Ad This will be a very long post as I will provide you with the exact way I achieved the original ad, as well as a prompt that get's you straight to the result in case you want to speed-run it. How I created the original: I made the ad collaborating with an agent. You can do this on the Runway platform, via the ChatGPT Runway Plugin or using Runway MCP. I asked the Agent the following: "Can you make a 30 second seedance 2.5 optimised prompt where the story is someone on vacation (beach/zipline/kayaking/hotairballoon/etc.) gets texted by his boss for one final change ASAP. They then look slightly concerned followed by the camera zooming out to reveal a vast landscape. Make sure to end on a super wide shot so that taglines can be added." It ran some thoughts by me, and as I genuinely didn't expect this to blow up, I just blindly let it do its thing and told the agent to start the video generation. The result is the one that you saw a few days ago. Keep in mind that results may vary, as many agents create personalized profiles of you based on their previous conversations. Once you have a prompt/result you like, you can go back to the agent and ask something like the following to get more variations: "What are other funny situations we can do that use the exact same structure?" ------------------------------ You can also skip all that, as I am sharing the exact prompt I used below. I used Seedance 2.5 set to 30 sec duration for my ads. 720p gives you that $9 ad, however you can also run it at 1080p for a more final production spec asset. You can also give the prompt to an LLM and ask it to make new narrative scenarios, using the exact same prompt structure. 🧵 Prompt is in the thread below! 🧵 Thank you for all the love on the ad. I've already seen a bunch of spin-offs, and can't wait to see even more.

Nicolas Neubert

67,568 просмотров • 1 месяц назад

🎬 Trailer: Genesis (Midjourney + Runway) We gave them everything. Trusted them with our world. To become enslaved - become hunted. We have no choice. Humanity must rise again to reclaim. Images: Midjourney Videos: #Runway Music: Pixabay / Stringer_Bell Edited in: CapCut

🎬 Trailer: Genesis (Midjourney + Runway) We gave them everything. Trusted them with our world. To become enslaved - become hunted. We have no choice. Humanity must rise again to reclaim. Images: Midjourney Videos: #Runway Music: Pixabay / Stringer_Bell Edited in: CapCut

Nicolas Neubert

1,782,774 просмотров • 3 лет назад

Here’s another $9, and telling Agent to do a new version featuring a knight instead. It’s that easy. Who wants the prompt?

Here’s another $9, and telling Agent to do a new version featuring a knight instead. It’s that easy. Who wants the prompt?

Nicolas Neubert

46,582 просмотров • 1 месяц назад

Super Intelligence only did half of this artwork.

Super Intelligence only did half of this artwork.

Nicolas Neubert

16,615 просмотров • 12 дней назад

This is not Unreal Engine 5. This is generated from scratch using AI.

This is not Unreal Engine 5. This is generated from scratch using AI.

Nicolas Neubert

178,316 просмотров • 8 месяцев назад

It's crazy what you can do in 2 hours with $100.

It's crazy what you can do in 2 hours with $100.

Nicolas Neubert

240,126 просмотров • 1 год назад

"How would it feel if the player found some ancient ruins in the jungle?" You can answer that question within 15 minutes by creating a starting frame with Frames and then extending it through prompting in Gen-4. Explore options, polish ideas, finalize it in engine.

"How would it feel if the player found some ancient ruins in the jungle?" You can answer that question within 15 minutes by creating a starting frame with Frames and then extending it through prompting in Gen-4. Explore options, polish ideas, finalize it in engine.

Nicolas Neubert

236,116 просмотров • 1 год назад

Generative World Models running in Real-Time are one of the many incredible research efforts at Runway that excite me every single day. It will be incredibly interesting to see what new genre of games this tech will spawn.

Generative World Models running in Real-Time are one of the many incredible research efforts at Runway that excite me every single day. It will be incredibly interesting to see what new genre of games this tech will spawn.

Nicolas Neubert

19,406 просмотров • 1 месяц назад

P H A N T O M ✦ C L A I R

P H A N T O M ✦ C L A I R

Nicolas Neubert

88,089 просмотров • 8 месяцев назад

Introducing Gen-4.5 Image-to-Video. This one is special. Gen-4.5 renders movement in a very special way that feels different and intentional. This I2V update will not only help creatives tell stories in new ways, but also make those stories feel different. Available now.

Introducing Gen-4.5 Image-to-Video. This one is special. Gen-4.5 renders movement in a very special way that feels different and intentional. This I2V update will not only help creatives tell stories in new ways, but also make those stories feel different. Available now.

Nicolas Neubert

88,568 просмотров • 9 месяцев назад

Using Runway Character's API, I built a character with the entire map knowledge base of Bungie's latest title Marathon. It can read the screen, guide you to objectives, and help you decide which valuables to extract. Just a preview of how gaming will change with AI.

Using Runway Character's API, I built a character with the entire map knowledge base of Bungie's latest title Marathon. It can read the screen, guide you to objectives, and help you decide which valuables to extract. Just a preview of how gaming will change with AI.

Nicolas Neubert

67,305 просмотров • 7 месяцев назад

I see a lot of prompts these days that are incredibly long, often presented as the only way to get the most out of SOTA video models. While detailed prompts do offer greater control, simple prompts can still be immensely powerful and produce great shots without having to choreograph every second of the scene. Here’s an example: Cinematic Unreal Engine Scene, fighting against a large black demon monster with a flame sword, particles flying everywhere doing spectacular ultimate modes. Brutal finishers.. Unreal Engine cutscene. Filmgrain, low contrast, muted colors.

I see a lot of prompts these days that are incredibly long, often presented as the only way to get the most out of SOTA video models. While detailed prompts do offer greater control, simple prompts can still be immensely powerful and produce great shots without having to choreograph every second of the scene. Here’s an example: Cinematic Unreal Engine Scene, fighting against a large black demon monster with a flame sword, particles flying everywhere doing spectacular ultimate modes. Brutal finishers.. Unreal Engine cutscene. Filmgrain, low contrast, muted colors.

Nicolas Neubert

13,835 просмотров • 1 месяц назад

Let's shake some dust off. Something special is coming.

Let's shake some dust off. Something special is coming.

Nicolas Neubert

12,585 просмотров • 1 месяц назад