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。

my favorite life hack > find a lecture on youtube > get transcript from > paste it into gemini with this prompt: "Generate an image. Turn this transcript into a cheatsheet with key takeaways, and give final output as 9:16 image created by nano banana. [PASTE FULL TRANSCRIPT]"

Alex Prompter

282,176 subscribers

358,667 次观看 • 10 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

38 条评论

Alex Prompter 的头像

Alex Prompter10 个月前

The AI prompt library your competitors don't want you to find → Biggest collection of text & image prompts → Unlimited custom prompts → Lifetime access & updates Grab it before it's gone 👇

zagundo 的头像

zagundo10 个月前

Or you could shortcut by just dropping a YouTube link straight into @NotebookLM and then crafting your preferred prompt for an infographic. Here is what I made in no time at all from a “10-hour” video from @thecodercoder - “Build a startup landing page with HTML, CSS, JS”.

Timothy Murphy 的头像

Timothy Murphy10 个月前

NotebookLM can generate summaries of long YT videos which is super helpful.

Alex Prompter 的头像

Alex Prompter10 个月前

Yup it’s helpful

TruthtideTV 的头像

TruthtideTV10 个月前

Google is really cooking with this model.

Bitcoin Gazillionaire  的头像

Bitcoin Gazillionaire 10 个月前

Expanded off your idea. Thx!

Benjaminxu 的头像

Benjaminxu10 个月前

i tried and succeeded，it really works

Alex Prompter 的头像

Alex Prompter10 个月前

It’s insane

Benjaminxu 的头像

Benjaminxu10 个月前

incredible

CodeMerkur | 的头像

CodeMerkur |10 个月前

Gemini 3.0 is the best thing that happened after the Internet was invented

Alan 的头像

Alan10 个月前

🤢 prompt.

Austin S. Lin 的头像

Austin S. Lin10 个月前

thanks! made this from

McLov(Ai)n 的头像

McLov(Ai)n10 个月前

Why do people have to pay for transcripts??? Is this a hidden add? You can get any Transcript for free directly on the Youtube Video with just one click... Look on the right side of the image.

Bruno El Adm 🐊 的头像

Bruno El Adm 🐊10 个月前

Done nice hack, however loads of spelling mistakes

Ryan Indépendant 的头像

Ryan Indépendant10 个月前

Is transcript necessary when gemini can already fetch the transcript of youtube videos by itself...?

Alex Prompter 的头像

Alex Prompter10 个月前

it cannot(for autogenerated)

Sagar Devkate 的头像

Sagar Devkate9 个月前

this is insane!

Camilo Villa - Lujo.ai 的头像

Camilo Villa - Lujo.ai10 个月前

This is an amazing idea, thanks for sharing it. It is even easier as Gemini autoanalyzes the video and extracts the script if you paste the url of it. Making it very straight forward.

Cenk Tokgöz 的头像

Cenk Tokgöz10 个月前

🙏

toghu 的头像

toghu10 个月前

so cooool

Rowland 的头像

Rowland10 个月前

@screenshoter screenshot this

Benjaminxu 的头像

Benjaminxu10 个月前

great practice

Antonio Zennaro 的头像

Antonio Zennaro10 个月前

Top

Inferno 的头像

Inferno10 个月前

Good one

ZeroNarrative 的头像

ZeroNarrative10 个月前

You can get the transcript straight from YouTube. No need for ytscribe

Adam Drapkin 的头像

Adam Drapkin10 个月前

I love this!

Arya 的头像

Arya10 个月前

Gemini can already read it it's not needed.

G.I. 的头像

G.I.10 个月前

Is this legal? Plagiarism?

Mohammad AlFiky 的头像

Mohammad AlFiky10 个月前

Try with @NanoBanana

Mostafa Dehghani 的头像

Mostafa Dehghani10 个月前

Give it a bit… that "> get transcript from line will go away!

Chirag Joshi 的头像

Chirag Joshi10 个月前

@zarazhangrui Can you integrate this in ?

Avi Nahir 的头像

Avi Nahir10 个月前

I've just tested Gemini's infographs vs. NotebookLM's ones, and the latter are better.

Hoang Bien 的头像

Hoang Bien10 个月前

alternatively you can paste the youtube url to NotebookLM also

DDD Baron 的头像

DDD Baron9 个月前

。c

Nimesh 📚📈 (Business & Life Upgrades) 的头像

Nimesh 📚📈 (Business & Life Upgrades)10 个月前

How accurate is the result?

Ryan Sandler 的头像

Ryan Sandler10 个月前

Have you noticed this is better than NotebookLM’s infographic prompt?

The AI God 的头像

The AI God9 个月前

This is a solid workflow for turning long videos into visual summaries. A few tweaks that level it up: → Add "include timestamps for each key point" so you can jump back to the source → Ask for "one actionable takeaway per section" to make it more practical → Try Claude or ChatGPT for the cheatsheet text first, then feed that to Gemini for the image The 9:16 format is smart for saving to phone or sharing in stories. What types of lectures work best for you with this method?

Joe Grant 的头像

Joe Grant10 个月前

Now you can just paste the YouTube directly into Gemini for the transcript

相关视频

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."

Paul Couvert

168,434 次观看 • 10 个月前

i’ve built a telegram bot that extracts transcripts from any video on youtube and x. this is particularly useful for clippers fans. simply paste the video link and it will provide you with the full transcript. try it out here:

i’ve built a telegram bot that extracts transcripts from any video on youtube and x. this is particularly useful for clippers fans. simply paste the video link and it will provide you with the full transcript. try it out here:

ileri 𖣂

28,554 次观看 • 23 天前

Defuddle now returns Youtube transcripts! Paste a YouTube link into defuddle.md to get a markdown transcript with timestamps, chapters, and pretty good diarization! ...or if you just want to read it, try the new Reader mode in Obsidian Web Clipper powered by Defuddle.

Defuddle now returns Youtube transcripts! Paste a YouTube link into defuddle.md to get a markdown transcript with timestamps, chapters, and pretty good diarization! ...or if you just want to read it, try the new Reader mode in Obsidian Web Clipper powered by Defuddle.

kepano

343,192 次观看 • 6 个月前

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

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

416,926 次观看 • 2 年前

here's how to do this in 2 minutes: - upload 0% interest image to gemini - ask it to generate a 1:1 prompt - generate the image with nano banana pro - lipsync with veo / infinitetalk (open-source) - voice change with minimax audio congrats you just got yourself 0% interest.

here's how to do this in 2 minutes: - upload 0% interest image to gemini - ask it to generate a 1:1 prompt - generate the image with nano banana pro - lipsync with veo / infinitetalk (open-source) - voice change with minimax audio congrats you just got yourself 0% interest.

0x ROAS

15,926 次观看 • 7 个月前

Build your first game with Gemini 3.5 Flash. Translate everyday objects directly into interactive, digital experiences without complex 3D modeling. Start with a Nano Banana prompt, turn your image into a game in Canvas, and refine your vision for optimal gameplay.

Build your first game with Gemini 3.5 Flash. Translate everyday objects directly into interactive, digital experiences without complex 3D modeling. Start with a Nano Banana prompt, turn your image into a game in Canvas, and refine your vision for optimal gameplay.

Google Gemini

24,402,226 次观看 • 3 个月前

here is how to steal any ad/image legally open gemini, create 'Vision-to-JSON' Gem find any image/ad you like, copy it, paste it into the gem, hit enter. JSON keeps every detail intact way better than natural-language summaries. now tweak the json chatting with Gemini using natural language: - make the product bigger - swap the background to a kitchen - add a founder handoff moment whatever you want, you get an updated JSON. copy the updated json and open a fresh Gemini chat paste the JSON code and generate image using NB Pro. you’ve now rebuilt the ad from scratch with a fully editable blueprint want this 'SWIPE File' with same copy/paste method? comment "GEM" to get it, (must be following to get the DM)

here is how to steal any ad/image legally open gemini, create 'Vision-to-JSON' Gem find any image/ad you like, copy it, paste it into the gem, hit enter. JSON keeps every detail intact way better than natural-language summaries. now tweak the json chatting with Gemini using natural language: - make the product bigger - swap the background to a kitchen - add a founder handoff moment whatever you want, you get an updated JSON. copy the updated json and open a fresh Gemini chat paste the JSON code and generate image using NB Pro. you’ve now rebuilt the ad from scratch with a fully editable blueprint want this 'SWIPE File' with same copy/paste method? comment "GEM" to get it, (must be following to get the DM)

ViralOps

138,186 次观看 • 9 个月前

Introducing Image to App. Turn any image into a native mobile app. Just paste an image. Claude Code Opus 4.6 will design, code, deploy and translate a mobile app inspired by original design. We’ve used this internally a lot for consumer apps on iOS/Android.

Introducing Image to App. Turn any image into a native mobile app. Just paste an image. Claude Code Opus 4.6 will design, code, deploy and translate a mobile app inspired by original design. We’ve used this internally a lot for consumer apps on iOS/Android.

David Ch

173,647 次观看 • 5 个月前

Google's Nano Banana is incredible. How to turn any photo into a 3D AI figure: 1. Open Gemini and select 2.5 Flash 2. Upload your image 3. Click “Create images” Use this exact prompt (in comments):

Google's Nano Banana is incredible. How to turn any photo into a 3D AI figure: 1. Open Gemini and select 2.5 Flash 2. Upload your image 3. Click “Create images” Use this exact prompt (in comments):

Alex Banks

26,591 次观看 • 1 年前

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

Ethan Mollick

137,469 次观看 • 1 年前

🙌 Love this Nano Banana 2 2 use case, inspired by a team at UCLA's Glitch Hacks hackathon tonight! Upload an image (or have NanoBanana simplify a more complex image) in Google AI Studio, then turn it into a step-by-step drawing guide with instructions + images interleaved:

🙌 Love this Nano Banana 2 2 use case, inspired by a team at UCLA's Glitch Hacks hackathon tonight! Upload an image (or have NanoBanana simplify a more complex image) in Google AI Studio, then turn it into a step-by-step drawing guide with instructions + images interleaved:

👩‍💻 Paige Bailey

17,603 次观看 • 5 个月前

You know that super annoying overlay texture pattern you get on AI images, particularly with Nano Banana Pro and GPT 2.0? Here's how to get rid of it. Toss your image into Magnific as a reference, select the Nano Banana Pro model, and prompt: Recreate this image exactly, detail for detail and restore fidelity, making it high resolution, and crisp, and clear. Exactly maintain the original colors. Credit to David LaChance, Jr. for figuring this out. Hope this helps.

You know that super annoying overlay texture pattern you get on AI images, particularly with Nano Banana Pro and GPT 2.0? Here's how to get rid of it. Toss your image into Magnific as a reference, select the Nano Banana Pro model, and prompt: Recreate this image exactly, detail for detail and restore fidelity, making it high resolution, and crisp, and clear. Exactly maintain the original colors. Credit to David LaChance, Jr. for figuring this out. Hope this helps.

Jordan Daniel Chesney

31,709 次观看 • 4 个月前

just found another guy posting the same content but on Youtube🚨 he did everything GOOD: 1- saw a format that was already working 2- replicated it with minimum changes 3- copied topics and uploaded 60 shorts and got +10 Million views CalliopeLabs template follows the SAME logic the short below was conceptualized, generated, edited and rendered by an AI follow this exact STEPS: > Copy the template in Calliope > Transcript 1 of his videos (free tools out there) > Generate a topic with Gemini/Chtgpt from it > Paste it and click on Generate you will get a video like this one 👇🏼 Follow + comment “tutorial” and i’ll send you a 3min vid on how to use (and create) this templates with CalliopeLabs ;)

just found another guy posting the same content but on Youtube🚨 he did everything GOOD: 1- saw a format that was already working 2- replicated it with minimum changes 3- copied topics and uploaded 60 shorts and got +10 Million views CalliopeLabs template follows the SAME logic the short below was conceptualized, generated, edited and rendered by an AI follow this exact STEPS: > Copy the template in Calliope > Transcript 1 of his videos (free tools out there) > Generate a topic with Gemini/Chtgpt from it > Paste it and click on Generate you will get a video like this one 👇🏼 Follow + comment “tutorial” and i’ll send you a 3min vid on how to use (and create) this templates with CalliopeLabs ;)

Sergio Gil

17,709 次观看 • 7 个月前

29 years ago, we were playing Final Fantasy VII, mesmerized by its graphics and gameplay. Today, we generate it with Google's new AI video model, Genie 3, by uploading a single image (generated by Nano Banana Pro). This is WILD:

29 years ago, we were playing Final Fantasy VII, mesmerized by its graphics and gameplay. Today, we generate it with Google's new AI video model, Genie 3, by uploading a single image (generated by Nano Banana Pro). This is WILD:

Alex Patrascu

40,353 次观看 • 7 个月前

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Get Gemini up to speed on what matters most to you with memory import. Bring an understanding of your key preferences, relationships, and personal context directly into Gemini. Once you import these memories, Gemini will understand the same key facts you’ve shared with other AI apps, like your dietary restrictions, your sibling’s names, or where you grew up and securely save those details for your next chat. To get started: 1) Head to your Settings in Gemini and select “Import memory to Gemini.” 2) Ask your current AI: Copy our suggested prompt and paste it into your other AI app to generate a summary of your preferences and style. 3) Copy the response: Copy the personalized summary it creates for you. 4) Paste into Gemini: Go back to “Import memory to Gemini,” paste the text, and start a new chat.

Google Gemini

49,038 次观看 • 5 个月前

A fun experiment for academics: Paste your favorite paper into Gemini 2.5 (assuming open rights) and ask it to turn it into a working game with "Canvas" turned on. This was in one go, I just trimmed out the waiting times from the video. I love the references to specific tables.

A fun experiment for academics: Paste your favorite paper into Gemini 2.5 (assuming open rights) and ask it to turn it into a working game with "Canvas" turned on. This was in one go, I just trimmed out the waiting times from the video. I love the references to specific tables.

Ethan Mollick

122,992 次观看 • 1 年前

These girls just revealed the AI workflow they use to monetize YouTube while living in Bali Here’s how they explain their workflow in the video: > They find viral kids’ videos on YouTube (in niches where creators can earn anywhere from $1,000 to $5,000 per million views) > They open the video’s transcript and copy it > They paste it into ChatGPT and ask it to generate a prompt for creating a similar video > They take that prompt, paste it into Picsart Flow, choose a video model (they use Sora 2 Pro in the video) and generate the content > They publish the finished video and collect the views They simply took a format that had already proven to work and turned ChatGPT plus an AI video generator into their own content production studio If you want to learn another way to create YouTube videos with AI, check out the article I linked below The author uses a completely different set of tools, so it’s worth a read Save this so you can find it later

These girls just revealed the AI workflow they use to monetize YouTube while living in Bali Here’s how they explain their workflow in the video: > They find viral kids’ videos on YouTube (in niches where creators can earn anywhere from $1,000 to $5,000 per million views) > They open the video’s transcript and copy it > They paste it into ChatGPT and ask it to generate a prompt for creating a similar video > They take that prompt, paste it into Picsart Flow, choose a video model (they use Sora 2 Pro in the video) and generate the content > They publish the finished video and collect the views They simply took a format that had already proven to work and turned ChatGPT plus an AI video generator into their own content production studio If you want to learn another way to create YouTube videos with AI, check out the article I linked below The author uses a completely different set of tools, so it’s worth a read Save this so you can find it later

Bonsai 🌳

33,993 次观看 • 2 个月前

A 2-hour podcast has maybe 6 minutes of gold in it. The problem was always finding those 6 minutes. Here's how I turn a full podcast into a finished thread in 5 minutes flat: Paste the YouTube link into HypeScribe It spits back the full transcript + a bullet summary in seconds I ask it: "give me the 5 most quotable, non-obvious moments" It pulls them with the exact timestamps and context I draft the thread straight from its answers No scrubbing. No rewatching at 1.5x hoping I catch the good part. The transcript is the boring half. The part that actually changed my workflow: I can talk to the content "what did they disagree on?", "summarize the second guest's argument", "rewrite this as a hook." It answers from the source, not from thin air. Works on TikTok, IG, X, Loom links too. 100+ languages.

A 2-hour podcast has maybe 6 minutes of gold in it. The problem was always finding those 6 minutes. Here's how I turn a full podcast into a finished thread in 5 minutes flat: Paste the YouTube link into HypeScribe It spits back the full transcript + a bullet summary in seconds I ask it: "give me the 5 most quotable, non-obvious moments" It pulls them with the exact timestamps and context I draft the thread straight from its answers No scrubbing. No rewatching at 1.5x hoping I catch the good part. The transcript is the boring half. The part that actually changed my workflow: I can talk to the content "what did they disagree on?", "summarize the second guest's argument", "rewrite this as a hook." It answers from the source, not from thin air. Works on TikTok, IG, X, Loom links too. 100+ languages.

xIA

21,574 次观看 • 2 个月前