正在加载视频...

视频加载失败

返回首页

I told Codex to "compose a concerto" using GPT-6 Astra just to see what would happen. It composed "Lanterns at the Water", a three-movement miniature concerto for piano and string orchestra, and generated MIDI, editable MusicXML scores, and a synthesized audio preview. I asked for a creative visualization and...

mhmazur's profile picture

Matt Mazur

5,745 subscribers

15,990 次观看 • 5 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I asked GPT 6 Astra to compose a piano melody and build a 3D pianist to play it and holy fuck, the fingers do follow the actual notes PLUS this ONLY took about 2h
3:49

I asked GPT 6 Astra to compose a piano melody and build a 3D pianist to play it and holy fuck, the fingers do follow the actual notes PLUS this ONLY took about 2h

Leon Lin

268,905 次观看 • 6 天前

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad
0:56

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

Om Patel

29,618 次观看 • 2 个月前

I asked my clawdbot to send a letter to me in the mail… and it actually did it. I gave it a crypto wallet and some USDC to make purchases with, and clawdbot went and read the agent documentation on postalform. It figured out how to draft an order with a PDF of the letter it wrote to me – then it used Stripe’s Purl cli and paid for the order using Stripe's new Machine Payments protocol. This is a huge step forward for real-world agentic task completion and commerce
0:51

I asked my clawdbot to send a letter to me in the mail… and it actually did it. I gave it a crypto wallet and some USDC to make purchases with, and clawdbot went and read the agent documentation on postalform. It figured out how to draft an order with a PDF of the letter it wrote to me – then it used Stripe’s Purl cli and paid for the order using Stripe's new Machine Payments protocol. This is a huge step forward for real-world agentic task completion and commerce

Gabriel Garrett

36,180 次观看 • 6 个月前

WAN 3.0 just changed how I think about AI video. I tested the Text to Video model on the Pika API Club. I gave it a prompt describing a woman on a motorbike riding into the horizon at dusk, and it delivered a full 30 second cinematic scene with native audio baked in and precise motion from start to finish. I did not have to stitch anything together or run a separate audio pass. It just handled everything. I used it on the Pika API Club at 35% off other platforms and off the official price. You can give a try here:
0:30

WAN 3.0 just changed how I think about AI video. I tested the Text to Video model on the Pika API Club. I gave it a prompt describing a woman on a motorbike riding into the horizon at dusk, and it delivered a full 30 second cinematic scene with native audio baked in and precise motion from start to finish. I did not have to stitch anything together or run a separate audio pass. It just handled everything. I used it on the Pika API Club at 35% off other platforms and off the official price. You can give a try here:

Oluwatimileyin✨🦋

68,691 次观看 • 18 天前

I'm oddly proud and stoked about this one - live video preview w/ audio of the Robotron AI training on the web. You can watch it live here: I started simple yesterday, a canvas I updated with a snapshot of the game that I pumped over a socket from an emulator session. That evolved into a video tag with a properly encoded video stream, and today I spent a full damned day almost adding audio and keeping it in sync with the game (which runs at an uncorked and unpredictable framerate). Assuming my machine can handle the load, it's available for viewing pleasure now at the link above :-) You have to click on the preview to enable the audio, and you can turn it off/on at the bottom of the page. Thanks to dsobeski for beta-testing it!
0:41

I'm oddly proud and stoked about this one - live video preview w/ audio of the Robotron AI training on the web. You can watch it live here: I started simple yesterday, a canvas I updated with a snapshot of the game that I pumped over a socket from an emulator session. That evolved into a video tag with a properly encoded video stream, and today I spent a full damned day almost adding audio and keeping it in sync with the game (which runs at an uncorked and unpredictable framerate). Assuming my machine can handle the load, it's available for viewing pleasure now at the link above :-) You have to click on the preview to enable the audio, and you can turn it off/on at the bottom of the page. Thanks to dsobeski for beta-testing it!

Dave W Plummer

15,271 次观看 • 6 个月前

I generated the audio first. Not the video. Ship announcement, ambient hum, rising score, the exact moment before a warp jump. One prompt, in Seed Audio 1.0. Then I fed that audio into Seedance and let it build the entire bridge scene around it. Camera, motion, the jump itself, all timed to sound that already existed. This is not TTS. This is directing a scene with sound before a single frame exists. 🔊 sound on and enjoy the trip
1:15

I generated the audio first. Not the video. Ship announcement, ambient hum, rising score, the exact moment before a warp jump. One prompt, in Seed Audio 1.0. Then I fed that audio into Seedance and let it build the entire bridge scene around it. Camera, motion, the jump itself, all timed to sound that already existed. This is not TTS. This is directing a scene with sound before a single frame exists. 🔊 sound on and enjoy the trip

Leila 👩🏻‍💻

33,164 次观看 • 2 个月前

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.
0:30

I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol. I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while. I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday. Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it. The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :) The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.

ilker

56,896 次观看 • 5 天前

I asked jason (DevEx at OpenAI): “What’s the craziest thing Codex did for you?” Here’s his answer: “I was on a bike ride when a coworker asked me to fix a launch video. So I connected remotely from my phone and asked Codex to use computer use to edit the video, export it, and post it back to Slack. Twenty minutes later, there was a new video in the Slack thread. Then I told Codex: ‘Every 30 minutes, check the thread for feedback and export V2, V3, V4.’ By the time I got home, the launch video was greenlit.” Codex had handled the revisions by repeatedly checking Slack for feedback. 📌 Watch the full episode here:
0:36

I asked jason (DevEx at OpenAI): “What’s the craziest thing Codex did for you?” Here’s his answer: “I was on a bike ride when a coworker asked me to fix a launch video. So I connected remotely from my phone and asked Codex to use computer use to edit the video, export it, and post it back to Slack. Twenty minutes later, there was a new video in the Slack thread. Then I told Codex: ‘Every 30 minutes, check the thread for feedback and export V2, V3, V4.’ By the time I got home, the launch video was greenlit.” Codex had handled the revisions by repeatedly checking Slack for feedback. 📌 Watch the full episode here:

Peter Yang

79,504 次观看 • 1 个月前

"King Sam The Pudding King" People were asking how I got the dancers in the previous video to move to the beat the trick is to include the key praise "The supplied song/audio file must guide the timing The movement should feel like a big [Music video style] with lively ensemble choreography, strong musical staging, and a bold finish." Along with your audio sample I find a blank video with just audio works best. I included one of the prompts In used in this clip below to give you an idea on how to use it. Sponsored and made with Invideo
0:36

"King Sam The Pudding King" People were asking how I got the dancers in the previous video to move to the beat the trick is to include the key praise "The supplied song/audio file must guide the timing The movement should feel like a big [Music video style] with lively ensemble choreography, strong musical staging, and a bold finish." Along with your audio sample I find a blank video with just audio works best. I included one of the prompts In used in this clip below to give you an idea on how to use it. Sponsored and made with Invideo

Captain HaHaa

22,787 次观看 • 3 个月前

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.
0:46

Seedance 2.0 is allowing us to enter a new era of music video creation. Here is how I created HONEY. It was a quick test to see how well this workflow holds up. 🐝 1 - Write your song and generate the music with Suno 5.5. 2 - Use an image generator of your choice. For HONEY I combined both Grok Imagine for aesthetics and Nano Banana Pro for refined editing. 3 - In Capcut I import my audio and just save out a blank video video containing the audio. This step is important because this video file containing audio will now be used with Seedance 2.0 as a video reference with Omni. This allows the AI to apply automatic and realistic lipsync and movement to the music, it's extremely powerful! 4 - Once I have a both my image and video with audio as reference, I use Seedance 2.0 Omni and upload my starting image and then the video reference with the audio. 5 - From here I'm simply prompting like normal, specifying what's happening in my scene with detailed instructions, mentioning multi shots and camera angle changes and then specifying that the person is singing along to the song. I type out the lyrics that are present to have better lipsync accuracy. 6 - Once I have generated a video and like the result, I do video to video, so i upload that video that just got generated and type "The scene continues" and prompt new actions to take place. This allows you to expand on a narrative. These new shots can be used as B-ROLL and since I uploaded my video as reference I have full consistency of everything it saw in the video. This is also extremely powerful. 7 - This is actually the most difficult part. Edit in Capcut. This is where you need to understand pacing and shot selection from all the scenes you generated to bring it all together. You must be strategic with the editing. Goodluck! I'll probably record a video tutorial at some point as it's easier to see what is being done.

Travis Davids

19,236 次观看 • 4 个月前

Grok Grok Bot can play the piano or any MIDI controller. I instructed it to compose in a romantic style with slow, soothing rhythms and play it on my Roland.
0:22

Grok Grok Bot can play the piano or any MIDI controller. I instructed it to compose in a romantic style with slow, soothing rhythms and play it on my Roland.

Yun-Ta Tsai

12,551 次观看 • 3 天前

I mentioned previously that I had been working for a couple months now on a system for applying AI to music theory. It's one of my few closed-source projects. It's a combination of a Rust cli tool, mtdt (music_theory_data_tool), which handles all mechanical aspects of importing and exporting and manipulating music in any format (midi, PDF, MusicXML, audio, etc.), and a huge skills library which is based on massive amounts of academic music theory and more. I asked the system to create a Bach fugue using GPT-6 Astra and the mtdt tool and the relevant skills, and it created the following. Notably, this didn't involve any external software other than mtdt, including the creation of the print-ready PDF score. It can do much, much more than this though. It can take a melody and write counterpoint for it, grounded in the theory, and using the mtdt tool to help it mechanically explore the space of "legal" possibilities while using its skills and intelligence to make artistic choices. It can make a ragtime version of a midi file. It can take a piano piece and re-orchestrate it for a brass band or string quartet. It covers a huge amount of stuff across over 300 skills. I'm not sure what I will do with the system ultimately, but I envisioned it as being an AI workstation for professional composers and musicians. You can see in the screenshot that it does a huge amount of intermediate work that is inspectable and legible; it's intentionally NOT a black box. Instead of outsourcing the entire musical process end-to-end like Suno, this system is about augmenting the creative human with as much or as little automation as desired. I continue to work on it with a couple agents every single day and it will keep getting better and better, and then with each new model release it will be better able to leverage the vast amount of expertise and knowledge about music that is already embedded in its cli tool and skills library.
3:34

I mentioned previously that I had been working for a couple months now on a system for applying AI to music theory. It's one of my few closed-source projects. It's a combination of a Rust cli tool, mtdt (music_theory_data_tool), which handles all mechanical aspects of importing and exporting and manipulating music in any format (midi, PDF, MusicXML, audio, etc.), and a huge skills library which is based on massive amounts of academic music theory and more. I asked the system to create a Bach fugue using GPT-6 Astra and the mtdt tool and the relevant skills, and it created the following. Notably, this didn't involve any external software other than mtdt, including the creation of the print-ready PDF score. It can do much, much more than this though. It can take a melody and write counterpoint for it, grounded in the theory, and using the mtdt tool to help it mechanically explore the space of "legal" possibilities while using its skills and intelligence to make artistic choices. It can make a ragtime version of a midi file. It can take a piano piece and re-orchestrate it for a brass band or string quartet. It covers a huge amount of stuff across over 300 skills. I'm not sure what I will do with the system ultimately, but I envisioned it as being an AI workstation for professional composers and musicians. You can see in the screenshot that it does a huge amount of intermediate work that is inspectable and legible; it's intentionally NOT a black box. Instead of outsourcing the entire musical process end-to-end like Suno, this system is about augmenting the creative human with as much or as little automation as desired. I continue to work on it with a couple agents every single day and it will keep getting better and better, and then with each new model release it will be better able to leverage the vast amount of expertise and knowledge about music that is already embedded in its cli tool and skills library.

Jeffrey Emanuel

37,552 次观看 • 2 天前

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

58,841 次观看 • 11 个月前

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.
0:36

I can't believe this worked! I saw the new poster for Neuromancer and thought: "What a cool font! Can I recreate it with AI?" I went to ChatGPT using GPT-6 Astra, and I gave the poster and this prompt: "Create a full font similar to the one in the attached poster, and animate a showcase presentation for the font using the Higgsfield plugin" It even did two versions of the font: Regular and Signal Fully usable, perfectly working fonts. It took 13m 19s to make all of this.

Alex Patrascu

19,492 次观看 • 3 天前

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.
0:50

It took me less than 10 minutes to create this scene. The longest part was finding the style for my initial image. I used Grok Imagine's extension video to ensure perfect continuity of style, voice, and music. Then I animated it, prompting in my native language without asking for any dialogue. Grok understood everything I asked and created a dialogue between the children in perfect French. I later posted the same children with a prompt in English, and this time, the dialogue was in English. I used Grok Imagine to create the image, animate it, and then extend the video to 30 seconds. I then started again with an image that I modified through editing and used it to tell another story.

Déborah

501,454 次观看 • 6 个月前

Our very own Alexander Chen created "Hello, world" a short film inspired by the technology of his childhood with Google Labs Flow. Here's a closer look at how he brought his vision to life: 1) All of the clips were generated in Flow using text-to-image prompts except he used image-to-video prompts for the close-up shots to ensure consistency and accuracy (and the images used were generated by Imagen). 2) To evoke the exact feelings of his childhood home, he used Google Street View for visual references then asked the Google Gemini to write descriptions and prompts, then uploaded those into Flow which is what produced such vivid and accurate renderings in the film. 3) Every sound used in the video is generated by Veo 3. However, to blend things together, he used a separate video editing software to extend the head and tail of each clip over the proceeding and following clip, occasionally crossfading the audio to help with transitions.
2:13

Our very own Alexander Chen created "Hello, world" a short film inspired by the technology of his childhood with Google Labs Flow. Here's a closer look at how he brought his vision to life: 1) All of the clips were generated in Flow using text-to-image prompts except he used image-to-video prompts for the close-up shots to ensure consistency and accuracy (and the images used were generated by Imagen). 2) To evoke the exact feelings of his childhood home, he used Google Street View for visual references then asked the Google Gemini to write descriptions and prompts, then uploaded those into Flow which is what produced such vivid and accurate renderings in the film. 3) Every sound used in the video is generated by Veo 3. However, to blend things together, he used a separate video editing software to extend the head and tail of each clip over the proceeding and following clip, occasionally crossfading the audio to help with transitions.

Google AI

94,790 次观看 • 1 年前

How to edit videos with GPT-6 Astra: 1. Install the ChatCut plugin in ChatGPT/Codex 2. Select GPT-6 Astra 3. Upload your footage 4. Describe the video you want Astra understands your footage and edits it directly in ChatCut. Every cut, caption, and motion graphic stays editable on a real timeline. This screen recording shows the entire setup and a short-video edit from start to finish. Comment “Chat” to get the plugin.
0:42

How to edit videos with GPT-6 Astra: 1. Install the ChatCut plugin in ChatGPT/Codex 2. Select GPT-6 Astra 3. Upload your footage 4. Describe the video you want Astra understands your footage and edits it directly in ChatCut. Every cut, caption, and motion graphic stays editable on a real timeline. This screen recording shows the entire setup and a short-video edit from start to finish. Comment “Chat” to get the plugin.

ChatCut

30,978 次观看 • 2 天前