正在加载视频...

视频加载失败

返回首页

References is so good that it allows the creation of interactive video games, like the old Myst titles, using Gen-3 Start and End frames for transitions Runway Cristóbal Valenzuela

alexfredo87's profile picture

Alex

1,770 subscribers

49,573 次观看 • 1 年前 •via X (Twitter)

科学技术游戏
LIVE

Anya Rossi• Live Now

Private livecam show

5 条评论

Chris Hackett 的头像
Chris Hackett1 年前

@runwayml @c_valenzuelab That is wild af

ASTROMEDA - Wishlist on Steam! 的头像
ASTROMEDA - Wishlist on Steam!2 年前

A small teaser of Astromeda! It's a game inspired by Pokemon, Undertale, and OneShot. Wishlist on Steam! #TrailerTuesday #indiegame #IndieGameDev #GamingNews #Steam

Adam Wagner 的头像
Adam Wagner1 年前

@runwayml @c_valenzuelab Cool idea. I miss those puzzle games.

FILM6AI 的头像
FILM6AI1 年前

@runwayml @c_valenzuelab 💯

TriforceKid7 的头像
TriforceKid71 年前

@runwayml @c_valenzuelab Awesome and very doable! I made an interactive (non-game) video recently using a single clip and navigation by programming the playhead for UI actions

相关视频

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!
1:08

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!

Weights & Biases

367,588 次观看 • 8 个月前

Nano Banana (To change the hairstyle + facial expressions) + Kling AI 2.1 Start & End Frames feature. Just experimenting and having some fun. I've experimented with keyframe features across so many different services but damn, using start and end frames with 2.1 is honestly amazing! Well done Kling, so much potential here for some fun transitions.
0:20

Nano Banana (To change the hairstyle + facial expressions) + Kling AI 2.1 Start & End Frames feature. Just experimenting and having some fun. I've experimented with keyframe features across so many different services but damn, using start and end frames with 2.1 is honestly amazing! Well done Kling, so much potential here for some fun transitions.

Travis Davids

25,944 次观看 • 11 个月前

Last Friday, Always Generating and I challenged ourselves to pull together a music video in just 2 hours using References and Gen-4. Also, Cristóbal Valenzuela wanted a floating cat. Here's the final result, starring none other than Bryan Fox!
1:16

Last Friday, Always Generating and I challenged ourselves to pull together a music video in just 2 hours using References and Gen-4. Also, Cristóbal Valenzuela wanted a floating cat. Here's the final result, starring none other than Bryan Fox!

Nicolas Neubert

20,022 次观看 • 1 年前

My extended video of Shenmue 1 using Gen-3 vid2vid is done. Hope you guys like it! Shenmue Forever #Shenmue Runway #LetsGetShenmue4
3:33

My extended video of Shenmue 1 using Gen-3 vid2vid is done. Hope you guys like it! Shenmue Forever #Shenmue Runway #LetsGetShenmue4

Alex

2,055,383 次观看 • 1 年前

Building virtual sets on top of reality, moving around in them and seeing them transformed entirely with Gen AI. Is this the future? :D This was quite simple to make actually: Figmin XR running on my Quest 3, using some models from sketchfab and some custom creations to set-dress my hallway. Filming a small performance of walking through the set and then using Runway Gen 3 to transform that. I'm still missing a lot of control with the AI process, like uploading style frames along the duration of the video.. but overall this is pretty incredible! Can't help but think about how insane it would have been to be able to use Dreams for stuff like this! What do you think? #art #ai
0:34

Building virtual sets on top of reality, moving around in them and seeing them transformed entirely with Gen AI. Is this the future? :D This was quite simple to make actually: Figmin XR running on my Quest 3, using some models from sketchfab and some custom creations to set-dress my hallway. Filming a small performance of walking through the set and then using Runway Gen 3 to transform that. I'm still missing a lot of control with the AI process, like uploading style frames along the duration of the video.. but overall this is pretty incredible! Can't help but think about how insane it would have been to be able to use Dreams for stuff like this! What do you think? #art #ai

Martin Nebelong

81,989 次观看 • 1 年前

Learn how ChatGPT works, in 7 mins, from the person who built it! I am so proud to share this video. We spent weeks fretting over every detail to make a video fit for all ages. Starring Mira Murati from OpenAI and Cristóbal Valenzuela from Runway, this is the best way to grasp how Large Language Models and chatbots work.
7:20

Learn how ChatGPT works, in 7 mins, from the person who built it! I am so proud to share this video. We spent weeks fretting over every detail to make a video fit for all ages. Starring Mira Murati from OpenAI and Cristóbal Valenzuela from Runway, this is the best way to grasp how Large Language Models and chatbots work.

Hadi Partovi

123,061 次观看 • 3 年前

"All My Noise" was selected for the AI&Human section at the Ars Electronica Animation Festival 2024. The original project was created in February using live action, SDXL and Runway Gen-2, and it was redone two days ago using Gen-3 Alpha Full Short:
2:12

"All My Noise" was selected for the AI&Human section at the Ars Electronica Animation Festival 2024. The original project was created in February using live action, SDXL and Runway Gen-2, and it was redone two days ago using Gen-3 Alpha Full Short:

Tomas Garcia

17,670 次观看 • 2 年前

I've been obsessing over Runway Gen-4.5 this past week. I tested it quite extensively, and I noticed a few things that should be fundamental to any video model: 1. Amazing spatial awareness. It just knows what comes next in the scene and renders it perfectly, with the correct distance, geometry, and style. 2. It understands the space and time. For example, how a character interacts with the environment, even if you don't prompt for it: High altitude > Windy. 3. This spatial sense of motion and place makes it look natural and cinematic. Regarding this last point, I've said it many times here on X that Runway needs to get out of the slow-motion era, and in the end, they delivered massively on it. It's just beautiful to watch scenes come to life naturally. Now, we just need sound and 1080p. Cristóbal Valenzuela take your time, we're here.
1:30

I've been obsessing over Runway Gen-4.5 this past week. I tested it quite extensively, and I noticed a few things that should be fundamental to any video model: 1. Amazing spatial awareness. It just knows what comes next in the scene and renders it perfectly, with the correct distance, geometry, and style. 2. It understands the space and time. For example, how a character interacts with the environment, even if you don't prompt for it: High altitude > Windy. 3. This spatial sense of motion and place makes it look natural and cinematic. Regarding this last point, I've said it many times here on X that Runway needs to get out of the slow-motion era, and in the end, they delivered massively on it. It's just beautiful to watch scenes come to life naturally. Now, we just need sound and 1080p. Cristóbal Valenzuela take your time, we're here.

Alex Patrascu

16,141 次观看 • 6 个月前

"I don't deny that creation looks old. I deny that it is that old. I believe the entire narrative of Genesis 1-3 is absolutely historical." From the Ask Anything Tour. You can watch more videos like this at the link:
1:57

"I don't deny that creation looks old. I deny that it is that old. I believe the entire narrative of Genesis 1-3 is absolutely historical." From the Ask Anything Tour. You can watch more videos like this at the link:

Albert Mohler

29,143 次观看 • 8 个月前

EDIT MOTION IN VIDEOS!!! Quit prompting and start directing I've been shouting for YEARS about 3D as the control layer. Here it is, signs of life of our Universal Video Editor!!! The workflow is: take your video, capture with comic 4, edit with the motion editor, re-render with your favorite video to video model (e.g., Runway and Google Gemini have good ones) Here we have a fashion clip where we wanted our actress to high step and show a bit more pizzaz - but shoot day is over, and traditionally it would cost many thousands to reshoot. Watch the video to see how it works instead in cartwheel. cc Logan Kilpatrick Cristóbal Valenzuela 👀
0:20

EDIT MOTION IN VIDEOS!!! Quit prompting and start directing I've been shouting for YEARS about 3D as the control layer. Here it is, signs of life of our Universal Video Editor!!! The workflow is: take your video, capture with comic 4, edit with the motion editor, re-render with your favorite video to video model (e.g., Runway and Google Gemini have good ones) Here we have a fashion clip where we wanted our actress to high step and show a bit more pizzaz - but shoot day is over, and traditionally it would cost many thousands to reshoot. Watch the video to see how it works instead in cartwheel. cc Logan Kilpatrick Cristóbal Valenzuela 👀

Andrew Carr 🤸

11,622 次观看 • 1 个月前

🎬 Midjourney v7 + Kling + Gen-4 + Udio: Showreel Midjourney v7 is out, so I decided to do a quick video showcasing the new model. We've had a great time recently with the release of Gen-4 as well, so this is my first video using both of these wonderful tools. Images: Midjourney v7 Video: Kling AI and Gen-4 Runway Music: Udio v1.5 Editing: CapCut
0:32

🎬 Midjourney v7 + Kling + Gen-4 + Udio: Showreel Midjourney v7 is out, so I decided to do a quick video showcasing the new model. We've had a great time recently with the release of Gen-4 as well, so this is my first video using both of these wonderful tools. Images: Midjourney v7 Video: Kling AI and Gen-4 Runway Music: Udio v1.5 Editing: CapCut

Everett World

47,039 次观看 • 1 年前

KLING is BEST on Higgsfield. KING is in the building! SMARTEST Start & End frames with the HIGHEST quality of 1080p. High IQ Transitions & High Aesthetic Morphs. Retweet to get the FULL Kling guide in your DMs. THE King is here to serve you. Let it.
0:39

KLING is BEST on Higgsfield. KING is in the building! SMARTEST Start & End frames with the HIGHEST quality of 1080p. High IQ Transitions & High Aesthetic Morphs. Retweet to get the FULL Kling guide in your DMs. THE King is here to serve you. Let it.

Higgsfield AI 🧩

878,813 次观看 • 11 个月前

So it doesn't matter what the context is right Chester Missing? First the video, then an old tweet. For someone who hates the word, you do end up using it a lot. God forbid that Chapter 9 institution discovers this.
0:32

So it doesn't matter what the context is right Chester Missing? First the video, then an old tweet. For someone who hates the word, you do end up using it a lot. God forbid that Chapter 9 institution discovers this.

Renaldo “Ngamla” Gouws 🇿🇦

42,591 次观看 • 1 年前

The new Dropbox brand website is so good 👏 I think it's one of the few scroll-based websites I've really enjoyed using because of how incredibly slick and interactive it is Have a play:
1:14

The new Dropbox brand website is so good 👏 I think it's one of the few scroll-based websites I've really enjoyed using because of how incredibly slick and interactive it is Have a play:

luis.

49,086 次观看 • 1 年前

🎬Midjourney + Runway + Hailuo AI + Udio: "Softly Dreaming" (AI music video) Dreamy winter LEGO vibes are the best - whenever I generate something like that, I feel so much younger! Both Hailuo and Gen-3 were useful here, but Hailuo's ability to generate natural videos of cars, ships, and other vehicles is so smooth and natural. Images: Midjourney v 6.1 Video: Gen-3 and Hailuo AI (MiniMax) Music: Udio Editing: CapCut
0:32

🎬Midjourney + Runway + Hailuo AI + Udio: "Softly Dreaming" (AI music video) Dreamy winter LEGO vibes are the best - whenever I generate something like that, I feel so much younger! Both Hailuo and Gen-3 were useful here, but Hailuo's ability to generate natural videos of cars, ships, and other vehicles is so smooth and natural. Images: Midjourney v 6.1 Video: Gen-3 and Hailuo AI (MiniMax) Music: Udio Editing: CapCut

Everett World

14,214 次观看 • 1 年前

2. Use the generated image as an image prompt for Runway or any video model that supports End-Frames. Use the image as the final/last frame and create a prompt that reveals the image in an ink-style animation. Example prompt:
0:21

2. Use the generated image as an image prompt for Runway or any video model that supports End-Frames. Use the image as the final/last frame and create a prompt that reveals the image in an ink-style animation. Example prompt:

Halim Alrasihi

14,596 次观看 • 1 年前

For me, the most important part of video creation right now is consistency. So I created my own GPT to achieve that. It's called AI Cinematic Consistency—and today, I want to share it with you and test it publicly. Let me explain why this matters 🧵 And here is the video I created using it.
1:19

For me, the most important part of video creation right now is consistency. So I created my own GPT to achieve that. It's called AI Cinematic Consistency—and today, I want to share it with you and test it publicly. Let me explain why this matters 🧵 And here is the video I created using it.

Jesus Plaza

395,268 次观看 • 1 年前

Kling 2.5 is among the best video models at the moment. It very accurate when using start frames so you can easily stitch multiple videos together and make a continuous shot. It’s now available on Freepik (now Magnific)
0:41

Kling 2.5 is among the best video models at the moment. It very accurate when using start frames so you can easily stitch multiple videos together and make a continuous shot. It’s now available on Freepik (now Magnific)

Martin LeBlanc

93,015 次观看 • 10 个月前