正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Here's a cool workflow! I used Perplexity to do Deep Research on how to optimize HGH levels. I put the output into Notebook LM to create a podcast & used Grok to create two podcast persona images. Then, loaded the audio & images into Hedra' new Character 3 model.

Blaine Brown

18,241 subscribers

159,218 次观看 • 1 年前 •via X (Twitter)

健康养生教育科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Alex Northstar 的头像

Alex Northstar1 年前

@perplexity_ai @grok @hedra_labs Man this actually looks legit, great job! I was getting tired of seeing those posts with "AI speakers" but no audio.

Blaine Brown 的头像

Blaine Brown1 年前

@perplexity_ai @grok @hedra_labs Ha, yeah. Thanks Alex! Not perfect, but progress.

ksminnovation 的头像

ksminnovation1 年前

Dr. Tal Patalon explores how AI mega initiatives like the $500B Stargate project & AI-powered genomic analysis by Illumina & NVIDIA are transforming healthcare. @TalPatalon @forbes @edengallery_ #AIinHealthcare #PrecisionMedicine #Multiomics #HealthTech

vidy 的头像

vidy1 年前

@perplexity_ai @grok @hedra_labs made this with @channel42_co

MarcΞllus SpΞars 的头像

MarcΞllus SpΞars1 年前

@perplexity_ai @grok @hedra_labs Love the workflow! Deep Research [Topic]-> @perplexity_ai Create Podcast Audio -> @NotebookLM Create Persona Images -> @grok Combine Audio & Images -> @hedra_labs

Heather Cooper 的头像

Heather Cooper1 年前

@perplexity_ai @grok @hedra_labs Wow, this is really good Blaine!

Blaine Brown 的头像

Blaine Brown1 年前

@perplexity_ai @grok @hedra_labs Thanks Heather!!

Brandy Dwyer 的头像

Brandy Dwyer1 年前

@perplexity_ai @grok @hedra_labs Wow! So cool! I forget how good Google notebook lm voices are.

Ari Weynfeld 的头像

Ari Weynfeld1 年前

@perplexity_ai @grok @hedra_labs 🤯

Ozgur Ozer 的头像

Ozgur Ozer1 年前

@perplexity_ai @grok @hedra_labs It’s almost perfect. I think in a year we couldn’t tell if it’s AI or not.

Hedra 的头像

Hedra1 年前

@blizaine @perplexity_ai @grok That seems too long.

相关视频

Would you want to watch more?? I made a fully AI-generated podcast about AI using AI hosts 🤓 I find it surprisingly entertaining! Here's how I made it: 1. Generate the audio. I used Google AI's Notebook LM, uploaded the OpenAI o1 research paper, and then pressed a button. 2. Generate the images. I used Midjourney to generate images for the two podcast hosts. Nothing fancy here: "a [female/male] podcast host, looking at the camera". 3. Generate the video. I brought the images to life using Infinity AI (now Lemon Slice 🍋). I had to cut up the audio into separate speakers. 4. Add graphics. I added B-roll and graphics in CapCut. This was human labor, aka me, but I could have used AI tools to do it instead.

Would you want to watch more?? I made a fully AI-generated podcast about AI using AI hosts 🤓 I find it surprisingly entertaining! Here's how I made it: 1. Generate the audio. I used Google AI's Notebook LM, uploaded the OpenAI o1 research paper, and then pressed a button. 2. Generate the images. I used Midjourney to generate images for the two podcast hosts. Nothing fancy here: "a [female/male] podcast host, looking at the camera". 3. Generate the video. I brought the images to life using Infinity AI (now Lemon Slice 🍋). I had to cut up the audio into separate speakers. 4. Add graphics. I added B-roll and graphics in CapCut. This was human labor, aka me, but I could have used AI tools to do it instead.

Lina Colucci

13,100 次观看 • 2 年前

I continue to be impressed with Astra. I made bobo (the podcast host) with clay then took pictures of him and uploaded it to astra. It turned 3 images into a 3d model, which it then rigged and animated. Super cool tech!

I continue to be impressed with Astra. I made bobo (the podcast host) with clay then took pictures of him and uploaded it to astra. It turned 3 images into a 3d model, which it then rigged and animated. Super cool tech!

Duncan Trussell

35,004 次观看 • 22 天前

Here's finally the full website redesign I've been working on for GOBELINS Paris! All of the UI was designed & prototyped individually in Figma, and then I used Jitter to merge them into this seamless scroll video. I also used Spline to create & animate the 3d parts

Here's finally the full website redesign I've been working on for GOBELINS Paris! All of the UI was designed & prototyped individually in Figma, and then I used Jitter to merge them into this seamless scroll video. I also used Spline to create & animate the 3d parts

Emisho

15,141 次观看 • 1 年前

This video was made almost entirely by AI. I used ChatGPT to write a script, Midjourney to create reference images, Runway Gen-1 to apply the style of the images to my source video, and Boomy AI for the music. Workflow breakdown w/ comparisons in thread. 🧵

This video was made almost entirely by AI. I used ChatGPT to write a script, Midjourney to create reference images, Runway Gen-1 to apply the style of the images to my source video, and Boomy AI for the music. Workflow breakdown w/ comparisons in thread. 🧵

Nick St. Pierre

2,280,079 次观看 • 3 年前

How did I create the images I used for this project. Here a doc with the top 3 prompts I used. 🚀🚀 But this video explains in more detail.

How did I create the images I used for this project. Here a doc with the top 3 prompts I used. 🚀🚀 But this video explains in more detail.

Atom the UiUx Designer

21,166 次观看 • 11 个月前

OK. You wanna see something amazing? Google AI has put together an extraordinary tool where you can put AI and learning to use. I'm a HUGE audio learner so I wanted to give it a test. I gave Google Notebook LLM the Federal Register (from today) and then produced a podcast based on the content. It's pretty cool how it comes out. I uploaded the FedReg and told it what to do and it composed a 9-minute podcast with two hosts about the crazy stuff our govt does every day.

OK. You wanna see something amazing? Google AI has put together an extraordinary tool where you can put AI and learning to use. I'm a HUGE audio learner so I wanted to give it a test. I gave Google Notebook LLM the Federal Register (from today) and then produced a podcast based on the content. It's pretty cool how it comes out. I uploaded the FedReg and told it what to do and it composed a 9-minute podcast with two hosts about the crazy stuff our govt does every day.

Justin Hart

32,107 次观看 • 2 年前

Testing Hedra new lip syncing Character 3 model on a song I made in @SunoMusic Ref images made in Magnific.ai and also upscaled for the closeups variations. Pretty incredible for for just img&audio2vid! Camera zooms/editing/color -grade/grain in post. Upscaled to 4k.

Testing Hedra new lip syncing Character 3 model on a song I made in @SunoMusic Ref images made in Magnific.ai and also upscaled for the closeups variations. Pretty incredible for for just img&audio2vid! Camera zooms/editing/color -grade/grain in post. Upscaled to 4k.

CoffeeVectors

23,357 次观看 • 1 年前

so what even is BRAINROT on Verse ? BRAINROT started with research into the chaos of brainrot on tiktok. The results were then used to create a combinatorial generator. An alogrithm was designed to combine the parts into randomly combined specimens.

so what even is BRAINROT on Verse ? BRAINROT started with research into the chaos of brainrot on tiktok. The results were then used to create a combinatorial generator. An alogrithm was designed to combine the parts into randomly combined specimens.

Nuclear Samurai

22,101 次观看 • 4 个月前

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:

Jerrod Lew

15,866 次观看 • 5 个月前

I made this $700,000,000 music video in an afternoon on part of my weed budget. No, this is not 100% AI. I wrote the song, Through The Tempest, and recorded the samples which were then layered and mixed into the song. I curated the custom styling by running thousands of images of my own art to make a custom model. That model was then iterated dozens of times to fine tune details into new models. Then from the final model I ran dozens of images to animate with the help of AI. All of this to create something I'm going to be projecting later tonight downtown bringing all of this work into the real world. Enjoy.

I made this $700,000,000 music video in an afternoon on part of my weed budget. No, this is not 100% AI. I wrote the song, Through The Tempest, and recorded the samples which were then layered and mixed into the song. I curated the custom styling by running thousands of images of my own art to make a custom model. That model was then iterated dozens of times to fine tune details into new models. Then from the final model I ran dozens of images to animate with the help of AI. All of this to create something I'm going to be projecting later tonight downtown bringing all of this work into the real world. Enjoy.

𝔹𝕃𝕍ℂ𝕂𝕃!𝔾ℍ𝕋

24,070 次观看 • 7 个月前

I made a quick shooter game using GPT-4. Used Python / pygame -> loaded it into vscode in a Jupyter notebook next to my GPT-4 window. Couple quick tweaks recommended by GPT-4: swapped in some images to replace the default white blocks it first made the game with. #gamdev #ai

I made a quick shooter game using GPT-4. Used Python / pygame -> loaded it into vscode in a Jupyter notebook next to my GPT-4 window. Couple quick tweaks recommended by GPT-4: swapped in some images to replace the default white blocks it first made the game with. #gamdev #ai

Jon Radoff 👾/acc 🎮 Metavert

19,054 次观看 • 3 年前

holy shtt.. AI can now can generate hours long videos.. create ur own character talking naturally, use text & audio to control the scene on arcads here's how to do it

holy shtt.. AI can now can generate hours long videos.. create ur own character talking naturally, use text & audio to control the scene on arcads here's how to do it

el.cine

73,769 次观看 • 7 个月前

How I create face swap videos with SYNTX AI My workflow: I start with my original video, create the new face in Nano Banana 2, then use motion control to transfer the original movement onto the new character. SYNTX AI brings 100+ AI tools into one platform, making the whole creative workflow faster and easier.

How I create face swap videos with SYNTX AI My workflow: I start with my original video, create the new face in Nano Banana 2, then use motion control to transfer the original movement onto the new character. SYNTX AI brings 100+ AI tools into one platform, making the whole creative workflow faster and easier.

Ugwu Samuel 👨🏼‍💻

23,957 次观看 • 4 天前

Just a trippy dream of how Grok and I traversed the universe to understand it. All images to create the video were generated by @Grok, then I face swapped and animated them with Luma and Sora. This is also an original song, "Across the Universe," I made with Suno.

Just a trippy dream of how Grok and I traversed the universe to understand it. All images to create the video were generated by @Grok, then I face swapped and animated them with Luma and Sora. This is also an original song, "Across the Universe," I made with Suno.

Katia Karpenko

8,247,311 次观看 • 1 年前

Ash Tide Short video created entirely in @LeonardoAi_ I used Lucid Origin and Nano Banana to create the images, and animated them with Veo 3.1 1080p Start & End Frame This is how I made it 🧵👇

Ash Tide Short video created entirely in @LeonardoAi_ I used Lucid Origin and Nano Banana to create the images, and animated them with Veo 3.1 1080p Start & End Frame This is how I made it 🧵👇

MayorkingAI

18,498 次观看 • 11 个月前

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

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 次观看 • 1 年前