Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I'm playing around with generative AI tools and stitching them together into visual stories. Here I took the first few sentences of Pride and Prejudice and made it into a video. The gen stack used for this one: - Anthropic Claude took the first chapter, generated the scenes and...

karpathy's profile picture

Andrej Karpathy

4,345,955 subscribers

610,937 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & TechnologieKunstBildung
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Andrej Karpathy
Andrej Karpathyvor 2 Jahren

Tried Runway Gen-3 now that they support image prompting. A lot better results on this scene. Dam this is fun. Now if I just tweak the prompt a little more and roll the dice again...

Profilbild von near
nearvor 2 Jahren

@AnthropicAI and just like that, an entire new genre of youtube videos was created from a single tweet

Profilbild von illusion diffusion
illusion diffusionvor 2 Jahren

@AnthropicAI 1. stable diffusion checkpoint/lora from @HelloCivitaior or @midjourney 2. @runwayml gen 3 or @KlingAIOfficial for image-to-vid 3. @elevenlabsio for voiceover/soundfx/folly 4. @sudo_ai or @udiomusic for bg music 5. non ai/premiere text overlay (no logo)

Profilbild von Andrej Karpathy
Andrej Karpathyvor 2 Jahren

@AnthropicAI @midjourney @runwayml @KlingAIOfficial @elevenlabsio @sudo_ai @udiomusic doh I totally forgot background music fail 🤦‍♂️

Profilbild von Felix Wang
Felix Wangvor 2 Jahren

@AnthropicAI Hey Andrej! I'm working on this exact problem: building an AI-native tool that integrates various models (LLMs, image, video, audio models) to help folks tell stories. Here's a video I made (the tool is at

Profilbild von Michael Kuliasov
Michael Kuliasovvor 2 Jahren

@AnthropicAI Tried similar thing a bit earlier too

Profilbild von Andrej Karpathy
Andrej Karpathyvor 2 Jahren

@AnthropicAI Very cool!!

Profilbild von AshutoshShrivastava
AshutoshShrivastavavor 2 Jahren

@AnthropicAI Andrej try out Gen-3.

Profilbild von Andrej Karpathy
Andrej Karpathyvor 2 Jahren

@AnthropicAI I'm trying! People seem to be getting really good results with it but I can't quite get that myself so far. It's kind of ignoring my instructions and generating videos that look way too modern, or just wrong or unrelated. I'll keep trying because the consistency is really great.

Profilbild von Dave Lee
Dave Leevor 2 Jahren

@AnthropicAI Yeah it's a big opportunity.

Ähnliche Videos

August 1, 2024: The Music Video Fun hack just stitching up gen AI tools :), in this case to create a music video for today. - copy paste the entire WSJ front page into Claude - ask it to generate multiple scenes and give visual descriptions for them - copy paste scene descriptions into image generator (Ideogram here) - copy paste generated images into Runway Gen 3 Alpha to make each image into a 10-second video - ask Claude to generate lyrics that depict that day - copy paste lyrics into Suno to generate music - stitch things up in iMovie :D :D :D
1:03

August 1, 2024: The Music Video Fun hack just stitching up gen AI tools :), in this case to create a music video for today. - copy paste the entire WSJ front page into Claude - ask it to generate multiple scenes and give visual descriptions for them - copy paste scene descriptions into image generator (Ideogram here) - copy paste generated images into Runway Gen 3 Alpha to make each image into a 10-second video - ask Claude to generate lyrics that depict that day - copy paste lyrics into Suno to generate music - stitch things up in iMovie :D :D :D

Andrej Karpathy

418,075 Aufrufe • vor 2 Jahren

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)
0:55

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,950 Aufrufe • vor 1 Jahr

Instead of watching 1 hour of Netflix today, watch this Stanford lecture by ex-GoogleBrain & OpenAI engineers. This is the best explanation of how LLMs like ChatGPT & Claude actually work, and how to unlock 100% of their potential. Worth watching whether you're a senior AI engineer or just taking your first steps in AI. I took the key ideas and turned them into a practical guide for getting 100% out of AI. You can find it below with ready-to-copy prompts and solutions.
1:16:28

Instead of watching 1 hour of Netflix today, watch this Stanford lecture by ex-GoogleBrain & OpenAI engineers. This is the best explanation of how LLMs like ChatGPT & Claude actually work, and how to unlock 100% of their potential. Worth watching whether you're a senior AI engineer or just taking your first steps in AI. I took the key ideas and turned them into a practical guide for getting 100% out of AI. You can find it below with ready-to-copy prompts and solutions.

Dhruv kumar

29,836 Aufrufe • vor 22 Tagen

Instead of watching 1 hour of Netflix today, watch this Stanford lecture by ex-GoogleBrain & OpenAI engineers. This is the best explanation of how LLMs like ChatGPT & Claude actually work, and how to unlock 100% of their potential. Worth watching whether you're a senior AI engineer or just taking your first steps in AI. I took the key ideas and turned them into a practical guide for getting 100% out of AI. You can find it below with ready-to-copy prompts and solutions.
1:16:28

Instead of watching 1 hour of Netflix today, watch this Stanford lecture by ex-GoogleBrain & OpenAI engineers. This is the best explanation of how LLMs like ChatGPT & Claude actually work, and how to unlock 100% of their potential. Worth watching whether you're a senior AI engineer or just taking your first steps in AI. I took the key ideas and turned them into a practical guide for getting 100% out of AI. You can find it below with ready-to-copy prompts and solutions.

Dhruv kumar

58,100 Aufrufe • vor 1 Monat

I just created this 36-second video in just five minutes with a simple prompt using Agent Mode in Grok Imagine All it took was a simple prompt, and it was made in just five minutes With a single image, it can generate matching scenes from different angles, build a full visual storyline, and even add subtitles. Grok Imagine Agent is one of the best tools for visual storytelling It's amazing how quickly you can now bring an idea to life just by expressing it in a few words The barrier between imagination and creation is getting smaller every day
0:36

I just created this 36-second video in just five minutes with a simple prompt using Agent Mode in Grok Imagine All it took was a simple prompt, and it was made in just five minutes With a single image, it can generate matching scenes from different angles, build a full visual storyline, and even add subtitles. Grok Imagine Agent is one of the best tools for visual storytelling It's amazing how quickly you can now bring an idea to life just by expressing it in a few words The barrier between imagination and creation is getting smaller every day

X Freeze

26,471 Aufrufe • vor 2 Monaten

Googles Omni Flash model is such a great combination with Dreams 3d artwork. For most of the generations here, simple prompts like these were all it took: "Wrap the video in stark realism" or "Wrap the video in the realism of the provided image". Reposting with the correct edit of the video. Ai workflows that allows us to push, pull, shape and move elemenrs around. Like clay, but powered by underlying world knowledge.. that's why I was excited about generative ai from the beginning - because I know there's plenty of room for us to raise the ceiling in our creative tools and workflows . I know I've been pushing this type of workflows for years and it's pretty crazy to see that the Ai systems we use are now at a level where this sort of workflow seems to be within reach.
0:39

Googles Omni Flash model is such a great combination with Dreams 3d artwork. For most of the generations here, simple prompts like these were all it took: "Wrap the video in stark realism" or "Wrap the video in the realism of the provided image". Reposting with the correct edit of the video. Ai workflows that allows us to push, pull, shape and move elemenrs around. Like clay, but powered by underlying world knowledge.. that's why I was excited about generative ai from the beginning - because I know there's plenty of room for us to raise the ceiling in our creative tools and workflows . I know I've been pushing this type of workflows for years and it's pretty crazy to see that the Ai systems we use are now at a level where this sort of workflow seems to be within reach.

Martin Nebelong

12,408 Aufrufe • vor 4 Monaten

Pretty CRAZY. one shot Claude code with a skill made this animated video of my essay with my voice. My input was the essay text and few APIs for image gen and voice. Less than an hour. 🤯 It has a few errors, pronunciations and images––all correctable with more prompts
2:22

Pretty CRAZY. one shot Claude code with a skill made this animated video of my essay with my voice. My input was the essay text and few APIs for image gen and voice. Less than an hour. 🤯 It has a few errors, pronunciations and images––all correctable with more prompts

Josh Wolfe

93,418 Aufrufe • vor 2 Monaten

For the past 6 weeks I was part of the Google Flow Sessions artist program where I developed this film using Google’s image and video models. This is the longest generative piece I’ve created to date, and it took days and days to put together. The tools keep improving, and I will continue experimenting with them. Will share more on the workflow next week. xx
3:41

For the past 6 weeks I was part of the Google Flow Sessions artist program where I developed this film using Google’s image and video models. This is the longest generative piece I’ve created to date, and it took days and days to put together. The tools keep improving, and I will continue experimenting with them. Will share more on the workflow next week. xx

𓁹‿𓁹

14,215 Aufrufe • vor 2 Monaten

Day 6 of building the game I've wanted to play for 15 years with AI. 3D models day. The first castles are in: a Hero Castle and a Human Castle. I'm attaching the build process of one of them, it shows my whole workflow. I took my time with this one and worked the details with soul. Generated separate pieces, assembled them into something I liked, textured the whole thing together, tweaked, polished, dropped it into the game. I can't stop staring at it. This is exactly what I wanted. Added animated flags on top. Ridiculously satisfying to watch. Then fog of war, plus a few mechanics fixes. Fog of war sent me straight back to childhood. I just sat there enjoying it and feeling nostalgic. I needed this part in the game. Also spent time on tree models and a few other assets. I'll show those tomorrow. The visual jump is big. I now simply like everything I see on screen.
1:03

Day 6 of building the game I've wanted to play for 15 years with AI. 3D models day. The first castles are in: a Hero Castle and a Human Castle. I'm attaching the build process of one of them, it shows my whole workflow. I took my time with this one and worked the details with soul. Generated separate pieces, assembled them into something I liked, textured the whole thing together, tweaked, polished, dropped it into the game. I can't stop staring at it. This is exactly what I wanted. Added animated flags on top. Ridiculously satisfying to watch. Then fog of war, plus a few mechanics fixes. Fog of war sent me straight back to childhood. I just sat there enjoying it and feeling nostalgic. I needed this part in the game. Also spent time on tree models and a few other assets. I'll show those tomorrow. The visual jump is big. I now simply like everything I see on screen.

Stefan 3D AI

26,347 Aufrufe • vor 1 Monat

Part 1/2 This one took me a while. I made the images in #Midjourney using a bunch of images for ref. I ran them through RUNWAY then used @lumaAI to create the transitions between each video. Music made with #Sunoai. #fyp #ai #aiart #aiimages #aivideo #aimusic #airt
2:20

Part 1/2 This one took me a while. I made the images in #Midjourney using a bunch of images for ref. I ran them through RUNWAY then used @lumaAI to create the transitions between each video. Music made with #Sunoai. #fyp #ai #aiart #aiimages #aivideo #aimusic #airt

Kelly Boesch🏳️‍🌈

17,728 Aufrufe • vor 2 Jahren

Day 18. Building the game I've dreamed of for 15 years with AI. I've learned how to build proper levels with AI. I take the design and the architecture, and AI helps me put it all together and check the balance. I made the first level of my game almost entirely by hand. I wanted to understand how it works and what I like, from how big the trees should be to how the textures tile. After a day digging around in the terrain tools it all made sense, and I could see how much of it could be automated by painting zones. Claude helped me a lot with the tileable textures. Matching the colors took a ton of iterations, and that was the hardest part of the whole level. For level two I took a different route. I built myself a simple HTML planner with a logical map of the level, where I place everything and design the layout. Painting a level and making it fun to play are two different jobs, so I kept the design for myself. We even made automated tests with Claude: 2D simulations that show which routes a player takes and how hard the level is. They're rough, but they give a real sense of how the level plays. Once the plan was ready, I handed everything to Claude, and 3-4 hours later I had a working level. It reused the patterns from my first level, scattered objects unevenly so nothing looks placed on a grid, and generated extra props whenever I asked. I showed it one example, it picked up what worked, and we turned that into a skill for the next levels. The video is a quick flight over level two, then how it got there, from my first sketch to the version I play now.
0:52

Day 18. Building the game I've dreamed of for 15 years with AI. I've learned how to build proper levels with AI. I take the design and the architecture, and AI helps me put it all together and check the balance. I made the first level of my game almost entirely by hand. I wanted to understand how it works and what I like, from how big the trees should be to how the textures tile. After a day digging around in the terrain tools it all made sense, and I could see how much of it could be automated by painting zones. Claude helped me a lot with the tileable textures. Matching the colors took a ton of iterations, and that was the hardest part of the whole level. For level two I took a different route. I built myself a simple HTML planner with a logical map of the level, where I place everything and design the layout. Painting a level and making it fun to play are two different jobs, so I kept the design for myself. We even made automated tests with Claude: 2D simulations that show which routes a player takes and how hard the level is. They're rough, but they give a real sense of how the level plays. Once the plan was ready, I handed everything to Claude, and 3-4 hours later I had a working level. It reused the patterns from my first level, scattered objects unevenly so nothing looks placed on a grid, and generated extra props whenever I asked. I showed it one example, it picked up what worked, and we turned that into a skill for the next levels. The video is a quick flight over level two, then how it got there, from my first sketch to the version I play now.

Stefan 3D AI

45,935 Aufrufe • vor 9 Tagen

A student built a whole faceless passive business by creating AI backyards. I kept seeing these AI backyard builds hitting 50M views and thought it took months of editing, but I was wrong. The creators aren't starting with a dirt lot. They start with the perfect final image and make the AI work backward. And the secret is stupidly simple: generate the final picture first, and let the AI reverse-engineer it. Here is the exact 3-step system you can use to build this: - The Blueprint: Upload your finished backyard to the "Restoration Timelapse" GPT. It reverse-engineers the final image into text prompts for the empty lot. - The Setup: Paste those prompts into Dzine. This generates your "before" images with perfectly matched geometry. - The Animation: Upload your empty lot and finished yard into Kling 3.0 to animate the build. Once Kling spits out the video file, drop it into CapCut, keep the raw construction audio, and export. I broke down the complete, step-by-step architecture with GPT + GROK + CAPCUT in my full guide below 👇
0:39

A student built a whole faceless passive business by creating AI backyards. I kept seeing these AI backyard builds hitting 50M views and thought it took months of editing, but I was wrong. The creators aren't starting with a dirt lot. They start with the perfect final image and make the AI work backward. And the secret is stupidly simple: generate the final picture first, and let the AI reverse-engineer it. Here is the exact 3-step system you can use to build this: - The Blueprint: Upload your finished backyard to the "Restoration Timelapse" GPT. It reverse-engineers the final image into text prompts for the empty lot. - The Setup: Paste those prompts into Dzine. This generates your "before" images with perfectly matched geometry. - The Animation: Upload your empty lot and finished yard into Kling 3.0 to animate the build. Once Kling spits out the video file, drop it into CapCut, keep the raw construction audio, and export. I broke down the complete, step-by-step architecture with GPT + GROK + CAPCUT in my full guide below 👇

Spivach

17,421 Aufrufe • vor 4 Monaten

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision
0:40

I created a 3D Gaussian Splat of my kitchen using 1/3rd the images it used to take me by using NVIDIA AI Developer's 3DGRUT! I can now use 180 degree fisheye images and ray tracing to make detailed splats. The only reason the scene isn't sharper is because my input images weren't super sharp - when I took the images back in October, I was still learning to use the lens. I plan to make a "first reactions/overview video". Tutorial after that. For reference, this took 206 images and the ultrawide on my iPhone took 608 images to capture. #3D #AEC #Computervision

Jonathan Stephens

30,717 Aufrufe • vor 1 Jahr

It took one conversation to build a complete content campaign. Hedra Agent managed the entire workflow—from concept to images, video, and final assets. No prompts. No switching between tools. No friction. This feels like the “coding agent” moment for visual content.
1:24

It took one conversation to build a complete content campaign. Hedra Agent managed the entire workflow—from concept to images, video, and final assets. No prompts. No switching between tools. No friction. This feels like the “coding agent” moment for visual content.

Muhammad Shahzad

110,134 Aufrufe • vor 6 Monaten

This is basically what it took to bring this video to life. Below are the prompts I used for character bible, shot list, camera direction, notes etc. Just copy and paste it into your favorite LLM and ask it to replace it with your character and world. 🌸
0:36

This is basically what it took to bring this video to life. Below are the prompts I used for character bible, shot list, camera direction, notes etc. Just copy and paste it into your favorite LLM and ask it to replace it with your character and world. 🌸

Glitter Gal

119,512 Aufrufe • vor 5 Monaten

This is an AI video. Made with Luma Luma Ray3. For the past couple of weeks, I've played with it, and I tried to give it the most challenging, but also very natural scenes. The result is unbelievable. Take a moment to realize that this is an AI video in 2025:
3:08

This is an AI video. Made with Luma Luma Ray3. For the past couple of weeks, I've played with it, and I tried to give it the most challenging, but also very natural scenes. The result is unbelievable. Take a moment to realize that this is an AI video in 2025:

Alex Patrascu

98,725 Aufrufe • vor 1 Jahr

UI/UX Designers, this might be one of the best sites for discovering trending AI prompts from X. Meigen gives you access to the hottest prompt posts weekly, including image and video generation prompts, all curated in one place for easy access and inspiration. You can even generate illustration images with one click and bring them into Figma for vectorization. Bookmark it for later 💜
0:56

UI/UX Designers, this might be one of the best sites for discovering trending AI prompts from X. Meigen gives you access to the hottest prompt posts weekly, including image and video generation prompts, all curated in one place for easy access and inspiration. You can even generate illustration images with one click and bring them into Figma for vectorization. Bookmark it for later 💜

Abraham John 🦄🦓

16,434 Aufrufe • vor 5 Monaten

It took me a bit, but I was able to dub and edit the first chapter of this comic dub! I honestly love the story and the artwork is just stellar! Thanks to ⛧ 𝙹𝚎𝚗 ( Comms- CLOSED ) for the go ahead! Special thanks to Katabelle Ansari | Kansas City 🏙️ and Ronald S. for their assistance with this dub!
5:10

It took me a bit, but I was able to dub and edit the first chapter of this comic dub! I honestly love the story and the artwork is just stellar! Thanks to ⛧ 𝙹𝚎𝚗 ( Comms- CLOSED ) for the go ahead! Special thanks to Katabelle Ansari | Kansas City 🏙️ and Ronald S. for their assistance with this dub!

Zack Trevle {VTuber and Script Writer} 🔞

49,276 Aufrufe • vor 11 Monaten

This is Pika 2.1 🤯 This is serendipitous as Pika was one of the first Gen AI video tools I ever used. The first time I generated a video on Discord, my life changed forever. And now they have released a game-changing new model with fantastic fidelity—native 1080p. We have arrived at the future of storytelling. And I'm glad they are part of our journey. Cheers.
0:48

This is Pika 2.1 🤯 This is serendipitous as Pika was one of the first Gen AI video tools I ever used. The first time I generated a video on Discord, my life changed forever. And now they have released a game-changing new model with fantastic fidelity—native 1080p. We have arrived at the future of storytelling. And I'm glad they are part of our journey. Cheers.

Dave Clark

22,341 Aufrufe • vor 1 Jahr