Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I vibe-v0⁠d a tool to replace a slower Figma workflow: creating a magnifying glass effect for my X screenshots. The entire image editor, draggable 🔍, resizable artboard, tooltip controls, copying / downloading logic, etc was prompted. Even the colors and gradient combinations were dreamt up by the LLM.

Guillermo Rauch

377,695 subscribers

74,533 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Guillermo Rauch1 year ago

Here's the image I downloaded

Matt Figdore2 years ago

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Guillermo Rauch1 year ago

Shipped: Fork it from v0 Community:

Prathamesh Shanbhag1 year ago

@v0 @figma @X Vibe V0ed. New term.

bl00dy🦇🔊 (🗿,🗿)1 year ago

@v0 @figma @X link or it didn't happen

Maxi Ferreira1 year ago

@v0 @figma @X This is really really cool! Is there a link to fork it? 🙏

Alexandru Ţurcanu1 year ago

@v0 @figma @X should make that a chrome extension!

Caleb1 year ago

@v0 @figma @X drop the link, I need this haha

George Mayer1 year ago

@v0 @figma @X Awesome. Crazy times. Sharable?

DONNY🔸1 year ago

@v0 @figma @X Did v0 do this @rauchg

Chris Lally | Fide ⬘1 year ago

@v0 @figma @X Appreciate the inspiration @rauchg

Related Videos

I built a multiplayer embroidery sampler for the internet. It's called Common Thread. 🪡 Built the entire thing in Figma Make, first thing I've ever vibecoded with it. Every visitor gets a patch on a shared canvas. You pick a thread color, choose a stitch type, and craft your art. A sampler is a piece of fabric where you practice and collect different stitches — a reference guide and playground in one. They were meant to be passed between hands and added to over time. Common Thread is that, but the fabric is infinite, the UI is whimsical, and the hands are anonymous. The part I love most: you can snap any section with a draggable embroidery hoop and export it, framed. i love how Figma Make is a kind of tool that lets you focus on what something should feel like, not how to ship it. Made for the Contra x Figma Makethon #FigmaMakeathon Try it yourself! /link below/

I built a multiplayer embroidery sampler for the internet. It's called Common Thread. 🪡 Built the entire thing in Figma Make, first thing I've ever vibecoded with it. Every visitor gets a patch on a shared canvas. You pick a thread color, choose a stitch type, and craft your art. A sampler is a piece of fabric where you practice and collect different stitches — a reference guide and playground in one. They were meant to be passed between hands and added to over time. Common Thread is that, but the fabric is infinite, the UI is whimsical, and the hands are anonymous. The part I love most: you can snap any section with a draggable embroidery hoop and export it, framed. i love how Figma Make is a kind of tool that lets you focus on what something should feel like, not how to ship it. Made for the Contra x Figma Makethon #FigmaMakeathon Try it yourself! /link below/

charlota

520,504 views • 5 months ago

After I finish a design project, the last thing I want to do is open Figma again just to make a post image. I usually default to a plain screenshot. That’s why I built Reframe. (Entirely in Figma Make!) Paste any image — and an entire grid of layout options generates instantly. Pick one. Edit. Copy. Post. No extra layout. No extra steps. Made for the Contra x #FigmaMakeathon Try it in link below👇

After I finish a design project, the last thing I want to do is open Figma again just to make a post image. I usually default to a plain screenshot. That’s why I built Reframe. (Entirely in Figma Make!) Paste any image — and an entire grid of layout options generates instantly. Pick one. Edit. Copy. Post. No extra layout. No extra steps. Made for the Contra x #FigmaMakeathon Try it in link below👇

DANN©

149,459 views • 5 months ago

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! :)

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 views • 10 months ago

Vibe coding a web-based MMORPG w/ Three.js update: ⚔️ Multiplayer combat ❤️‍🩹 Health tracking 🪄 Spell VFX updates The earthquake spell was co-designed by Anthropic claude-3.7-sonnet (thinking). I prompted the design for a few basic spells (fire ball, ice blast) in Cursor, then prompted to come up with a series of new ideas for spells, building upon the previous. The physics use

Vibe coding a web-based MMORPG w/ Three.js update: ⚔️ Multiplayer combat ❤️‍🩹 Health tracking 🪄 Spell VFX updates The earthquake spell was co-designed by Anthropic claude-3.7-sonnet (thinking). I prompted the design for a few basic spells (fire ball, ice blast) in Cursor, then prompted to come up with a series of new ideas for spells, building upon the previous. The physics use

Majid Manzarpour

77,230 views • 1 year ago

Growing up, I had a SNES while my buddy had a Genesis. So I only knew about Sega games through him and magazines. He didn't own Ecco the Dolphin, so I was only familiar from screenshots. I was very surprised years later to see the opening and learn about the eerie sci-fi vibe.

Growing up, I had a SNES while my buddy had a Genesis. So I only knew about Sega games through him and magazines. He didn't own Ecco the Dolphin, so I was only familiar from screenshots. I was very surprised years later to see the opening and learn about the eerie sci-fi vibe.

Elder Mathias

28,365 views • 1 month ago

Video shows a tsunami hitting a Russian town on Wednesday after a 8.8 magnitude earthquake off the country’s Far Eastern Kamchatka Peninsula. Buildings and other debris in the town of Severo-Kurlisk were seen washed inland by the strong waves as the entire shore was inundated. The powerful quake prompted the National Weather Service to issue a tsunami warning for Hawaii and parts of Alaska. A tsunami advisory was also issued for the entire West Coast, from the California-Mexico border up to the Alaska-British Columbia border.

Video shows a tsunami hitting a Russian town on Wednesday after a 8.8 magnitude earthquake off the country’s Far Eastern Kamchatka Peninsula. Buildings and other debris in the town of Severo-Kurlisk were seen washed inland by the strong waves as the entire shore was inundated. The powerful quake prompted the National Weather Service to issue a tsunami warning for Hawaii and parts of Alaska. A tsunami advisory was also issued for the entire West Coast, from the California-Mexico border up to the Alaska-British Columbia border.

CBS News

37,846 views • 1 year ago

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

I tried to see how far I could push my current AI + 3D workflow and build a playable 3D game prototype in just 3 days😶 Not by asking AI to make the whole game in one prompt. I had my own idea, knew what I wanted to build, and used AI as a tool: - for concepting, - asset generation & texturing, - gameplay logic with the new UE 5.8 MCP + Claude Code. And honestly, it is crazy how far you can get now with the right workflow. Full video - #UE5 #ClaudeCode #AI3D #3DAI

Stefan 3D AI

20,994 views • 1 month ago

The pitch wheel on my MIDI controller started drifting, so I got a 3rd party joycon to replace it, it's even got hall effect sticks so drifting shouldn't be a problem! Here's a sample of a tune I'm making for ABYSS X ZERO using this joycon!

The pitch wheel on my MIDI controller started drifting, so I got a 3rd party joycon to replace it, it's even got hall effect sticks so drifting shouldn't be a problem! Here's a sample of a tune I'm making for ABYSS X ZERO using this joycon!

IronFairy - Fernanda Dias

13,374 views • 1 year ago

The reason my rigging process is a bit slower is because even for something as simple as a single eye, I spend a lot of time adding multiple layers of deformation and creating at least 25+ parameters to make the movement as smooth and natural as possible.😋 #Live2D #Live2DWIP

The reason my rigging process is a bit slower is because even for something as simple as a single eye, I spend a lot of time adding multiple layers of deformation and creating at least 25+ parameters to make the movement as smooth and natural as possible.😋 #Live2D #Live2DWIP

✂️Sneko/Live2D Rigger♡/COMMS OPEN

16,260 views • 1 month ago

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

This might actually change everything 🫨 (no, for real). The 3D lighthouse you see was created in Blender using Claude 3.7, guided by my text prompts, and the reference image on the right - more below 👇 Manual adjustments were minimal - just basic repositioning/resizing of some elements (stretching lengths or widening diameters). Everything else - the primitives, shapes, colors, materials, lighting etc - was generated by the LLM itself. And this is only on day 1! Claude 3.7 wasn't even specifically designed for this. Imagine what a specialized LLM could achieve - one that better understands prompts & visual references or that could follow an artist’s manual guidance (“vibesculpting”) This is on Blender so far, but it feels clear that a similar process will apply to ALL creative software (3D, 2D, video…) and eventually… any software.

Emm | scenario.com

192,765 views • 1 year ago

I used Figma Make to build the most delightful link library and book cover configurator ever vibecoded. For the Contra x Figma Makeathon, I decided to build an app to turn my 47 open tabs into a beautiful book. Then I put it on a shelf for the whole internet to browse. It's called Stash For each collection, you have the opportunity to design the best cover ever using the in-app configurator. It has pencils, markers, stamps, graffiti... The entire thing is made in Figma, including stamps, illustrations, and graffiti artworks. I think this is my best public work so far and I hope it lets me leave a mark on the internet.

I used Figma Make to build the most delightful link library and book cover configurator ever vibecoded. For the Contra x Figma Makeathon, I decided to build an app to turn my 47 open tabs into a beautiful book. Then I put it on a shelf for the whole internet to browse. It's called Stash For each collection, you have the opportunity to design the best cover ever using the in-app configurator. It has pencils, markers, stamps, graffiti... The entire thing is made in Figma, including stamps, illustrations, and graffiti artworks. I think this is my best public work so far and I hope it lets me leave a mark on the internet.

Noman

30,679 views • 5 months ago

I wanted to make my own version of this but my tree model started glitching in and out of existence like crazy out of nowhere and after fixing it the editor froze for like twenty minutes and Unity ended up crashing I wish this was a bit but my entire PC was tweaking for a moment

I wanted to make my own version of this but my tree model started glitching in and out of existence like crazy out of nowhere and after fixing it the editor froze for like twenty minutes and Unity ended up crashing I wish this was a bit but my entire PC was tweaking for a moment

Yisuno ⚝ | SKARM BELIEVER

144,387 views • 18 days ago

I found a Claude skill that plans my entire AI ad before I even open Gemini Omni. I just send it: → the product → the ad style (LEGO, crochet, cartoon, Pixar, etc.) that’s it. a few seconds later it gives me: → a complete script → a scene-by-scene breakdown → Gemini Omni prompts ready to generate I don’t waste time figuring out what each scene should look like or rewriting prompts until they work. I just generate the ad. It’s the exact workflow I’ve been using to make AI ads for affiliate offers, and it’s cut my creation time by more than half. RT + comment “SKILL” and I’ll DM you the exact workflow I use to make these ads (Claude skill included). (must be following for DM)

I found a Claude skill that plans my entire AI ad before I even open Gemini Omni. I just send it: → the product → the ad style (LEGO, crochet, cartoon, Pixar, etc.) that’s it. a few seconds later it gives me: → a complete script → a scene-by-scene breakdown → Gemini Omni prompts ready to generate I don’t waste time figuring out what each scene should look like or rewriting prompts until they work. I just generate the ad. It’s the exact workflow I’ve been using to make AI ads for affiliate offers, and it’s cut my creation time by more than half. RT + comment “SKILL” and I’ll DM you the exact workflow I use to make these ads (Claude skill included). (must be following for DM)

Bruno

57,680 views • 18 days ago

Claude Cowork is like Claude Code but for your entire life It's going to be the biggest AI tool of 2026 I figured out a workflow that saves me 5+ hours a day and it's so simple even a non tech nerd can do it Here's my complete breakdown you can steal today:

Claude Cowork is like Claude Code but for your entire life It's going to be the biggest AI tool of 2026 I figured out a workflow that saves me 5+ hours a day and it's so simple even a non tech nerd can do it Here's my complete breakdown you can steal today:

Alex Finn

407,739 views • 6 months ago

"I had initially thought Gaza was attacked... A lot of people showed immediate support for palestine. One of the things I remember believing was that the majority of the people slaughtered that day were IDF soldiers... There was a lot of twisted logic to fit a more appetizing narrative. Leftists and progressives were pro Palestine out the gate. I just assumed I should too even if I don't know all the facts. There was no room for nuanced takes, it meant you were taking both sides and allowing Zionist propaganda to take effect on you" Taryn Thomas Former pro-palestine activist speaks out

"I had initially thought Gaza was attacked... A lot of people showed immediate support for palestine. One of the things I remember believing was that the majority of the people slaughtered that day were IDF soldiers... There was a lot of twisted logic to fit a more appetizing narrative. Leftists and progressives were pro Palestine out the gate. I just assumed I should too even if I don't know all the facts. There was no room for nuanced takes, it meant you were taking both sides and allowing Zionist propaganda to take effect on you" Taryn Thomas Former pro-palestine activist speaks out

Hamas Atrocities

27,003 views • 8 months ago

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,825 views • 3 months ago

This girl says she makes up to $5k creating cartoons using AI She revealed her “secret” to earning on YouTube with AI, and it honestly looks kind of scary In the video, she breaks down step by step her workflow that turns AI into a personal production studio: > Finding a “goldmine”: She looks for viral videos in the kids’ niche > Copying the foundation: She opens the description of the most popular video and basically copies its transcript > Creating a script: She pastes that text into ChatGPT and asks it to generate a detailed prompt for a similar kids show > Generating animation: She goes to Picsart AI Playground (or any other AI tool), selects a video generation tool, pastes the prompt from ChatGPT, and gets a fully made colorful cartoon > Monetization: She uploads the video to her channel and starts getting views And I was thinking - this could easily be automated with AI agents that do all these steps on their own and even upload directly to YouTube I already explained how to build a system like that in the article below Go check it out, save it and read it

This girl says she makes up to $5k creating cartoons using AI She revealed her “secret” to earning on YouTube with AI, and it honestly looks kind of scary In the video, she breaks down step by step her workflow that turns AI into a personal production studio: > Finding a “goldmine”: She looks for viral videos in the kids’ niche > Copying the foundation: She opens the description of the most popular video and basically copies its transcript > Creating a script: She pastes that text into ChatGPT and asks it to generate a detailed prompt for a similar kids show > Generating animation: She goes to Picsart AI Playground (or any other AI tool), selects a video generation tool, pastes the prompt from ChatGPT, and gets a fully made colorful cartoon > Monetization: She uploads the video to her channel and starts getting views And I was thinking - this could easily be automated with AI agents that do all these steps on their own and even upload directly to YouTube I already explained how to build a system like that in the article below Go check it out, save it and read it

Bonsai 🌳

105,959 views • 1 month ago

kimi: “well, i just look at the image, and i dont think he was even going to make the corner without ME. it was very optimistic, even locked up. also looking at the angle of his car, it was completely towards the wall. a shame my race was ruined” CLOCKK

kimi: “well, i just look at the image, and i dont think he was even going to make the corner without ME. it was very optimistic, even locked up. also looking at the angle of his car, it was completely towards the wall. a shame my race was ruined” CLOCKK

ًَ

215,815 views • 9 months ago

As of this this morning, there was Ksh377,000 on my Expressway ETC card for the vehicle I was given by Parliament. I honestly do not need all that money. Even if I ran up and down the expressway for a year, I would never exhaust that money - Edwin Sifuna

As of this this morning, there was Ksh377,000 on my Expressway ETC card for the vehicle I was given by Parliament. I honestly do not need all that money. Even if I ran up and down the expressway for a year, I would never exhaust that money - Edwin Sifuna

Kenyans.co.ke

53,372 views • 2 years ago