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.

Made a little web app ✨ 🎨 Create images containing words, phrases, or sentences using ⚡️ Powered by Gemini 2.0 Flash Experimental's native image gen + a self-correction loop to try again if it fails

Kaushik Shivakumar

3,451 subscribers

13,620 views • 1 year ago •via X (Twitter)

Science & Technology Arts

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemini 2.0 Flash ⚡️ has arrived! 2.0 Flash > 1.5 Pro (again!) 📈 Interacts with a browser 🤖 Native image generation 🖼️ and much more! Try it out As a preview of what is possible, wishing you all a Drastic Holiday powered by 2.0!

Gemini 2.0 Flash ⚡️ has arrived! 2.0 Flash > 1.5 Pro (again!) 📈 Interacts with a browser 🤖 Native image generation 🖼️ and much more! Try it out As a preview of what is possible, wishing you all a Drastic Holiday powered by 2.0!

Oriol Vinyals

41,377 views • 1 year ago

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

Lumina

72,529 views • 2 months ago

Every app eventually needs an image viewer. Somehow, most of them still feel janky on the web. I’ve been working on a composable Lightbox primitive - Base UI / Radix by WorkOS / shadcn style API, native-feeling transitions, touch gestures, pinch-to-zoom, keyboard support, and all the little details that make it feel real. Is this something you’d reach for?

Every app eventually needs an image viewer. Somehow, most of them still feel janky on the web. I’ve been working on a composable Lightbox primitive - Base UI / Radix by WorkOS / shadcn style API, native-feeling transitions, touch gestures, pinch-to-zoom, keyboard support, and all the little details that make it feel real. Is this something you’d reach for?

Artur Bień

35,902 views • 2 months ago

What’s in my bag? 🎀✨ It’s more than just a question — it’s a glimpse into imagination and creativity. This entire visual was created using GPT Image 2 × Seedance 2.0 on Pollo AI Mobile App 🤖✨ No photoshoot, no setup — just an idea turned into a stunning visual reality. From everyday thoughts to aesthetic storytelling, AI is changing the way we create content. Now it’s your turn — imagine your own version and bring it to life ⬇️

What’s in my bag? 🎀✨ It’s more than just a question — it’s a glimpse into imagination and creativity. This entire visual was created using GPT Image 2 × Seedance 2.0 on Pollo AI Mobile App 🤖✨ No photoshoot, no setup — just an idea turned into a stunning visual reality. From everyday thoughts to aesthetic storytelling, AI is changing the way we create content. Now it’s your turn — imagine your own version and bring it to life ⬇️

Lady Julia Ana 👸🏼

61,071 views • 5 months ago

I topped up $5 on an API aggregator ToAPIs Then I found out GPT Image 2 costs only around $0.015 per image. If you do a lot of testing or batch-generate commercial AI images, that difference adds up fast. I think I just found the secret to generating more, testing more, and spending less. And it’s not just one model. With the same key, you can access 50+ models for image, video, and text, including GPT Image 2, Gemini Omni, Seedance 2.0, Kling AI 3.0, grok-video-1.5-preview, and more. Some models are priced up to 80% lower than official platforms. Just top up and test what you need: Made on ToAPIs with GPT Image 2 + Seedance 2.0

I topped up $5 on an API aggregator ToAPIs Then I found out GPT Image 2 costs only around $0.015 per image. If you do a lot of testing or batch-generate commercial AI images, that difference adds up fast. I think I just found the secret to generating more, testing more, and spending less. And it’s not just one model. With the same key, you can access 50+ models for image, video, and text, including GPT Image 2, Gemini Omni, Seedance 2.0, Kling AI 3.0, grok-video-1.5-preview, and more. Some models are priced up to 80% lower than official platforms. Just top up and test what you need: Made on ToAPIs with GPT Image 2 + Seedance 2.0

Shami

22,991 views • 3 months ago

This is literally genius🤯 4.9 million views with this format And nobody even knows its a clanker they copied a viral format in the fashion space Easily automated it, this account alone could make $40,000/mo+ if they tie it to a fashion app And add a strong CTA anybody can replicate an AI account like this in 6 simple steps 1. Connect higgsfield MCP 2. Have nano banana create the base character 3. Have claude come up with a fashion line ( like Anime characters clothings ) 4. Have the higgs mcp generate 10 outfit variations images for claudes idea. 5. Generate all the clips using seedance 2.0 from the start image of each outfit and the same base prompt for walking. 6. add a CTA somewhere in there to your fashion app congratulations you automated a fashion app to $40k/mo

This is literally genius🤯 4.9 million views with this format And nobody even knows its a clanker they copied a viral format in the fashion space Easily automated it, this account alone could make $40,000/mo+ if they tie it to a fashion app And add a strong CTA anybody can replicate an AI account like this in 6 simple steps 1. Connect higgsfield MCP 2. Have nano banana create the base character 3. Have claude come up with a fashion line ( like Anime characters clothings ) 4. Have the higgs mcp generate 10 outfit variations images for claudes idea. 5. Generate all the clips using seedance 2.0 from the start image of each outfit and the same base prompt for walking. 6. add a CTA somewhere in there to your fashion app congratulations you automated a fashion app to $40k/mo

Ernesto Lopez

100,375 views • 4 months ago

I was digging around the HyperCard 1.0.1 floppy image tonight, as one does, and found a curious private file: FONT 31756. It's a font file containing all of the glyphs for HyperCard's tool palette, likely created by Kristee Kreitman and Marge Boots (credited in the app for Graphic Art). I can't believe they were using this technique back in 1987, although it seems Bruce Tognazzini invented it with MouseText two years prior (!). I was moved, as I often am by the work of our field's forebears, so created this little tool for everyone to explore it here:

I was digging around the HyperCard 1.0.1 floppy image tonight, as one does, and found a curious private file: FONT 31756. It's a font file containing all of the glyphs for HyperCard's tool palette, likely created by Kristee Kreitman and Marge Boots (credited in the app for Graphic Art). I can't believe they were using this technique back in 1987, although it seems Bruce Tognazzini invented it with MouseText two years prior (!). I was moved, as I often am by the work of our field's forebears, so created this little tool for everyone to explore it here:

joshpuckett

52,024 views • 1 month ago

Vibe coding apps that require you to store and manage large files just got easier, with Replit ⠕ App Storage. ✨ My favorite example in this category are any PDF analysis apps: create a fully customized AI synthesizer in just a few prompts. App Storage is Replit's Object Storage solution (like Amazon S3 or Google CS). But don't worry if those words sound foreign to you, Agent will set this up for you automatically if your app needs it. On that note, this Agent capability is just the beginning of our efforts to make building apps with databases and storage easier: 👇

Vibe coding apps that require you to store and manage large files just got easier, with Replit ⠕ App Storage. ✨ My favorite example in this category are any PDF analysis apps: create a fully customized AI synthesizer in just a few prompts. App Storage is Replit's Object Storage solution (like Amazon S3 or Google CS). But don't worry if those words sound foreign to you, Agent will set this up for you automatically if your app needs it. On that note, this Agent capability is just the beginning of our efforts to make building apps with databases and storage easier: 👇

vic

27,313 views • 1 year ago

Most AI video tools are stuck in a loop, you generate, change the prompt, and wait again. Vidu S2 is pushing things forward by making generation interactive. You can edit the video while it is being created. Change the style, swap the background, or switch outfits in real time. If you drop in a new image, the video adjusts instantly without awkward cuts. Under the hood, it combines real time 720P output with an AI agent that actively watches the video to plan what happens next. It allows you to change reference images on the fly, powered by a model optimized specifically for live streaming. This opens up massive possibilities. Imagine viewers controlling visual changes during a livestream, people transforming into game characters, or shoppers trying on different looks live. The entire S Series is available for a free trial right now so you can test it yourself. Use my code PANDAS2 with the link below to grab 300 bonus credits to explore the other features. Vidu Stream: 300 Bonus Credits: Vidu AI #ViduAI #ViduS #ViduS2

Most AI video tools are stuck in a loop, you generate, change the prompt, and wait again. Vidu S2 is pushing things forward by making generation interactive. You can edit the video while it is being created. Change the style, swap the background, or switch outfits in real time. If you drop in a new image, the video adjusts instantly without awkward cuts. Under the hood, it combines real time 720P output with an AI agent that actively watches the video to plan what happens next. It allows you to change reference images on the fly, powered by a model optimized specifically for live streaming. This opens up massive possibilities. Imagine viewers controlling visual changes during a livestream, people transforming into game characters, or shoppers trying on different looks live. The entire S Series is available for a free trial right now so you can test it yourself. Use my code PANDAS2 with the link below to grab 300 bonus credits to explore the other features. Vidu Stream: 300 Bonus Credits: Vidu AI #ViduAI #ViduS #ViduS2

AI Panda

98,066 views • 17 days ago

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???

I spent my Astra tokens trying to teach small Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???

merve

22,903 views • 26 days ago

There’s no other way to describe it: Your child’s physical and intellectual growth between 12 and 24 months is exponential. At one year of age many children are speaking their first words and taking their first unsteady steps. A year later and you’ll hardly recognize them as the same child. Check out this little one (shown here approaching two) who manages to string together, not a word or two, but a six word sentence (requesting to be taken to her grandmother’s house). When her father asks her to repeat herself, she lays it on thick, adding a pair of extra pleases at the start of the sentence for good measure - extending her request to 8 words. Isn’t it amazing to think that less than 12 months earlier this little one likely spoke her first word? Such amazing growth in her vocabulary and sophistication. Kudos little one! Here’s hoping you made it over to grandma’s house. When did your baby speak their first words? Their first full sentences? This adorable language learner was shared to TT by rosemeblue_alllove.

There’s no other way to describe it: Your child’s physical and intellectual growth between 12 and 24 months is exponential. At one year of age many children are speaking their first words and taking their first unsteady steps. A year later and you’ll hardly recognize them as the same child. Check out this little one (shown here approaching two) who manages to string together, not a word or two, but a six word sentence (requesting to be taken to her grandmother’s house). When her father asks her to repeat herself, she lays it on thick, adding a pair of extra pleases at the start of the sentence for good measure - extending her request to 8 words. Isn’t it amazing to think that less than 12 months earlier this little one likely spoke her first word? Such amazing growth in her vocabulary and sophistication. Kudos little one! Here’s hoping you made it over to grandma’s house. When did your baby speak their first words? Their first full sentences? This adorable language learner was shared to TT by rosemeblue_alllove.

Dan Wuori

232,755 views • 2 years ago

DOM3 is made from HTML, CSS and Javascript, closer to a document than a canvas. It's a strange contemporary material that shapes much of our digital lives. The rhythm of endless creation and deletion in DOM3 is a self-driving version of what happens when you browse the web. "The Document Object Model (DOM) connects web pages to scripts or programming languages by representing the structure of a document—such as the HTML representing a web page—in memory." A html element, and a rectangle on a canvas, are not the same thing. It's a different material. Even if it all ends up controlling the same pixels, the process is different. The html element kind of actually exists, in this abstract context of a document object model. And in memory, in the moment. If it was possible to measure its weight, it would be heavier than a pixel on a canvas.

DOM3 is made from HTML, CSS and Javascript, closer to a document than a canvas. It's a strange contemporary material that shapes much of our digital lives. The rhythm of endless creation and deletion in DOM3 is a self-driving version of what happens when you browse the web. "The Document Object Model (DOM) connects web pages to scripts or programming languages by representing the structure of a document—such as the HTML representing a web page—in memory." A html element, and a rectangle on a canvas, are not the same thing. It's a different material. Even if it all ends up controlling the same pixels, the process is different. The html element kind of actually exists, in this abstract context of a document object model. And in memory, in the moment. If it was possible to measure its weight, it would be heavier than a pixel on a canvas.

Leander Herzog

11,484 views • 1 year ago

where to look: higgs 🎬 “if only i had means, i would be a tarkovsky” one of the sentences i heard most at university film clubs now if you have a solid idea, you can bring it to screen with a single prompt, without allocating a massive budget, with price like a netflix subscription, together with update brought by higgs’s seedance 2.0 there is something i always say “if you build, they will come” meaning if you bring your idea to life, you can get opportunity to work with big budget brands by licensing your ip but like in every field, being early matters here too. 2027 will probably be a period where this is already being showcased on tv. so listen to your feelings and thoughts and try to give them life with higgs (i made video you watched with a single prompt)

where to look: higgs 🎬 “if only i had means, i would be a tarkovsky” one of the sentences i heard most at university film clubs now if you have a solid idea, you can bring it to screen with a single prompt, without allocating a massive budget, with price like a netflix subscription, together with update brought by higgs’s seedance 2.0 there is something i always say “if you build, they will come” meaning if you bring your idea to life, you can get opportunity to work with big budget brands by licensing your ip but like in every field, being early matters here too. 2027 will probably be a period where this is already being showcased on tv. so listen to your feelings and thoughts and try to give them life with higgs (i made video you watched with a single prompt)

LANGERIUS

17,306 views • 5 months ago

Most robots still need markers, checkerboards, or long calibration rituals just to know where their arms are. Now it works from raw images in seconds. roboreg is a markerless multi arm localization toolkit that plugs into ROS 2 and RViz. No special hardware. No custom setup. You toggle between robot descriptions and the system figures out the rest. The idea is simple: ✅ Hand eye calibration from plain RGB or RGB D images ✅ Only three robot poses needed for millimeter accuracy ✅ Works with any ROS 2 compatible robot and camera ✅ Fully open source under Apache 2.0 It is powered by Hydra, a new marker free ICP variant that converges far more reliably than classical baselines and runs in under a second. If you want to try it: roboreg: ROS 2 roboreg: Hydra paper: pip install roboreg More details and discussion on Open Robotics Discourse:

Most robots still need markers, checkerboards, or long calibration rituals just to know where their arms are. Now it works from raw images in seconds. roboreg is a markerless multi arm localization toolkit that plugs into ROS 2 and RViz. No special hardware. No custom setup. You toggle between robot descriptions and the system figures out the rest. The idea is simple: ✅ Hand eye calibration from plain RGB or RGB D images ✅ Only three robot poses needed for millimeter accuracy ✅ Works with any ROS 2 compatible robot and camera ✅ Fully open source under Apache 2.0 It is powered by Hydra, a new marker free ICP variant that converges far more reliably than classical baselines and runs in under a second. If you want to try it: roboreg: ROS 2 roboreg: Hydra paper: pip install roboreg More details and discussion on Open Robotics Discourse:

Ilir Aliu

18,442 views • 10 months ago

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Everyone's sleeping on image-to-3D AI models. They can make your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!

Anshu

29,342 views • 3 months ago

How to use China's best AI video model (Seedance 2.0) completely free and without watermarks. Most people think you need expensive subscriptions or get stuck with watermarked outputs (mandatory in China). Not if you use this loophole. The Setup • VPN to Hong Kong/China (only to start download). • Download the "Doubao" app from doubao[dot]com. • Install (Android: allow from browser / iOS: switch appstore region to HK). • Register with a non-US phone number, if you're from US and need a SMS service DM me, I'll send you one. The "Glitch" Workflow The Seedance 2.0 feature in app often fails. Do this instead: • Toggle Image Model (Seedream 4.5). • Type your prompt. • Add this specific text at the end: "generate video, not the image". • Result: 10s video, bypassing the busy server errors. How to Remove the Watermark If you save directly, it stamps it. Here is the fix: • Tap Share → Copy Link. • Open that link in your mobile browser. • Long press video → Download. Congratulations, you just got the clean video without watermarks. Total Cost: $0 Daily Limit: 5 free videos per account This method is only one so far. Bookmark if you need this.

How to use China's best AI video model (Seedance 2.0) completely free and without watermarks. Most people think you need expensive subscriptions or get stuck with watermarked outputs (mandatory in China). Not if you use this loophole. The Setup • VPN to Hong Kong/China (only to start download). • Download the "Doubao" app from doubao[dot]com. • Install (Android: allow from browser / iOS: switch appstore region to HK). • Register with a non-US phone number, if you're from US and need a SMS service DM me, I'll send you one. The "Glitch" Workflow The Seedance 2.0 feature in app often fails. Do this instead: • Toggle Image Model (Seedream 4.5). • Type your prompt. • Add this specific text at the end: "generate video, not the image". • Result: 10s video, bypassing the busy server errors. How to Remove the Watermark If you save directly, it stamps it. Here is the fix: • Tap Share → Copy Link. • Open that link in your mobile browser. • Long press video → Download. Congratulations, you just got the clean video without watermarks. Total Cost: $0 Daily Limit: 5 free videos per account This method is only one so far. Bookmark if you need this.

Alchemiz

16,928 views • 7 months ago

🔥 VIDU Multi-Entity Consistency Give Vidu 2/3 images and it’ll turn them into a video—it’s pure magic! ✨ Your own characters interacting with objects and in the exact environment you want! Ads, movies… endless possibilities, and this is just the beginning! Thanks @Viduforhuman The future is a carrot! 🥕 Plus, how about grabbing any frame from a Vidu-generated video "from scratch" and throwing it into another AI video or image tool to push your project even further? For now, check out the comment below: I scaled up a frame with Magnific.ai and fed it into Runway to create a dynamic shot using full camera control. But fingers crossed I can soon use #ReCapture by Bisho & team to generate new shots from the same video!

🔥 VIDU Multi-Entity Consistency Give Vidu 2/3 images and it’ll turn them into a video—it’s pure magic! ✨ Your own characters interacting with objects and in the exact environment you want! Ads, movies… endless possibilities, and this is just the beginning! Thanks @Viduforhuman The future is a carrot! 🥕 Plus, how about grabbing any frame from a Vidu-generated video "from scratch" and throwing it into another AI video or image tool to push your project even further? For now, check out the comment below: I scaled up a frame with Magnific.ai and fed it into Runway to create a dynamic shot using full camera control. But fingers crossed I can soon use #ReCapture by Bisho & team to generate new shots from the same video!

Hungry Donkey 🥕

37,561 views • 1 year ago