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。

Automated UI testing feels like AGI in Devin 10 examples (running macOS + Linux Cloud Agents) 🧵 What happens (automatic for any update): • Creates programmatic test plan • Boots the app with secrets & credentials (auth, etc.) • Autonomously clicks, types, and checks the UI like a human... show more

nader dabit

193,984 subscribers

1,601,008 次观看 • 6 天前 •via X (Twitter)

科学技术教育游戏

Anya Rossi• Live Now

Private livecam show

28 条评论

nader dabit 的头像

nader dabit6 天前

2. E-commerce automated UI testing and in-browser bug reporting (end to end)

nader dabit 的头像

nader dabit6 天前

3. Testing a 2-player native iOS and Android game playing side by side simultaneously (macOS environment)

nader dabit 的头像

nader dabit6 天前

4. Testing a native macOS screen recording app with most features

nader dabit 的头像

nader dabit6 天前

5. End to end testing of a flow-chart app

nader dabit 的头像

nader dabit6 天前

6. Testing a native macOS, native iOS, and web-based multi-player chess game simultaneously

nader dabit 的头像

nader dabit6 天前

7. Running terminal apps and walking through the commands and file system

nader dabit 的头像

nader dabit6 天前

8. Building a native SwiftUI app, code-sign it, notarize with Apple via notarytool, staple the ticket, and package a signed DMG with drag-to-Applications window.

nader dabit 的头像

nader dabit6 天前

9. Testing slideshow app by creating, editing, and playing an entire slide deck

nader dabit 的头像

nader dabit6 天前

10. Testing and playing a native iOS game on real macOS hardware

nader dabit 的头像

nader dabit6 天前

Learn more about @devinai computer use here:

Alps 的头像

Alps6 天前

@cognition @DevinAI devin is has the most tasteful and accurate agents ever. Proud devin user ngl

austin 的头像

austin6 天前

@cognition @DevinAI Devin is still the best testing agent I’ve ever used

Rose Phamm 的头像

Rose Phamm6 天前

@cognition @DevinAI Chạy được cả trên macOS lẫn Linux Cloud Agents thì tiện thật, đỡ phải lo môi trường khác nhau 🌱

Marius du Preez 的头像

Marius du Preez6 天前

@cognition @DevinAI Mobile testing has been banger legit always tooo so long todo mobile shiz now its easy af

Hari 的头像

Hari6 天前

@cognition @DevinAI try

Saiyam Pathak 的头像

Saiyam Pathak6 天前

@cognition @DevinAI Devin keeps on creating the wow magic always!

Kien Trinh 的头像

Kien Trinh6 天前

@cognition @DevinAI cái vụ chạy trên cả macOS lẫn Linux cloud agents nghe tiện ghê, đỡ phải setup nhiều

Macro Bombastic 的头像

Macro Bombastic6 天前

@cognition @DevinAI honestly this is the part of ai that actually gets me hyped

POBE 🎀 的头像

POBE 🎀6 天前

@cognition @DevinAI automatic secrets and ui clicking sounds wild

Prince Kushwaha 的头像

Prince Kushwaha6 天前

@cognition @DevinAI Running simultaneous iOS and Android emulators on macOS cloud agents to test real-time multiplayer is an incredible benchmark for agentic testing.

Ariel Lillie 的头像

Ariel Lillie6 天前

@cognition @DevinAI love that it boots with credentials and clicks through ui checks

Devix 的头像

Devix6 天前

@cognition @DevinAI This is exciting ! 🔥🔥

AnAn Nguyenn 的头像

AnAn Nguyenn6 天前

@cognition @DevinAI Nghe như đang xem phim khoa học viễn tưởng mà lại là thật luôn á 😅

Hailu 🍏 的头像

Hailu 🍏6 天前

@cognition @DevinAI Devin thật ấn tượng, giống như tương lai vậy

AI Mastery Guide 的头像

AI Mastery Guide6 天前

@cognition @DevinAI does it handle auth flows well?

Brew 的头像

Brew6 天前

@cognition @DevinAI hey @dabit3 you never really finished giving out the 50 devin max accounts

Ryan 的头像

Ryan6 天前

@cognition @DevinAI Can alot of this been accomplished with the desktop app aswell or just the webapp? I can only see computer use option available in the webapp

john Harry 的头像

john Harry6 天前

@cognition @DevinAI How reliable is it in production?

相关视频

Underrated feature of advanced cloud agents like Devin: Infinitely parallelizable human-grade UI testing. They - Stand up a live environment with secrets - Inspect code changes - Plan a comprehensive end-to-end test - Handle real authentication + identity - Use computer vision + mouse-and-keyboard control to test the app through its actual user interface: full-journey app verification - Verify the expected behavior, and return a short annotated video as proof. They also preserve setup and testing knowledge as reusable skills, making future verification faster and more reliable.

Underrated feature of advanced cloud agents like Devin: Infinitely parallelizable human-grade UI testing. They - Stand up a live environment with secrets - Inspect code changes - Plan a comprehensive end-to-end test - Handle real authentication + identity - Use computer vision + mouse-and-keyboard control to test the app through its actual user interface: full-journey app verification - Verify the expected behavior, and return a short annotated video as proof. They also preserve setup and testing knowledge as reusable skills, making future verification faster and more reliable.

nader dabit

104,717 次观看 • 2 个月前

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

nader dabit

302,785 次观看 • 1 个月前

At the Giga Texas Test Track, we see some of it is being used now, with railed lanes, a long line of rumble strips, paint marks & cones … these are in the area where I showed a ground video yesterday of Cybercabs testing with acceleration runs. I’ve included a portion of that video in this one showing the location on the track. Speaking of Cybercab testing, we see 7 set up along with a trailer, that looks like the LIDAR testing rigs that usually we see on the roofs of vehicles driving around streets for camera validation testing & more in what seems to be a temporary dedicated testing facility until a more permanent one is completed. Still more asphalt work to complete the inner portions fo the track, but it is definitely partially operational now and being used! Very nice to see!

At the Giga Texas Test Track, we see some of it is being used now, with railed lanes, a long line of rumble strips, paint marks & cones … these are in the area where I showed a ground video yesterday of Cybercabs testing with acceleration runs. I’ve included a portion of that video in this one showing the location on the track. Speaking of Cybercab testing, we see 7 set up along with a trailer, that looks like the LIDAR testing rigs that usually we see on the roofs of vehicles driving around streets for camera validation testing & more in what seems to be a temporary dedicated testing facility until a more permanent one is completed. Still more asphalt work to complete the inner portions fo the track, but it is definitely partially operational now and being used! Very nice to see!

Joe Tegtmeyer 🚀 🤠🛸😎

18,784 次观看 • 3 个月前

Cybercab test track testing underway again today, this time using stop lights as well as stop signs. Great look at the action in this video clip along with some maintenance of one Cybercab at the testing operations centers. I also noted more Cybercabs, a lot of Model Y’s and YL’s and new Cybertrucks at the outbound lot and End-of-Line on the west side of the highway today. Check it out and have a great weekend!

Cybercab test track testing underway again today, this time using stop lights as well as stop signs. Great look at the action in this video clip along with some maintenance of one Cybercab at the testing operations centers. I also noted more Cybercabs, a lot of Model Y’s and YL’s and new Cybertrucks at the outbound lot and End-of-Line on the west side of the highway today. Check it out and have a great weekend!

Joe Tegtmeyer 🚀 🤠🛸😎

66,242 次观看 • 18 天前

I built an AI Factory that uses Claude Code agents to build apps while I sleep. This is an automated "assembly line" pipeline, all run by Claude Opus 4.5. Projects move through a Kanban-like system from Idea to Research, Architecture, Coding and Testing. Factory workers start with market research, searching the web and social media. Then they validate everything, checking app stores for competition and securing a domain name. (All automated by APIs and MCPs) They automatically create several rounds of app UI revisions. When I wake up, there are projects waiting for me to review: approve this design, give feedback, send that one back for improvement. Projects are actively coded and tested by the agents, while the entire process is tracked and logged (with "worker documents" that travel each step of the way, like a real factory.)

I built an AI Factory that uses Claude Code agents to build apps while I sleep. This is an automated "assembly line" pipeline, all run by Claude Opus 4.5. Projects move through a Kanban-like system from Idea to Research, Architecture, Coding and Testing. Factory workers start with market research, searching the web and social media. Then they validate everything, checking app stores for competition and securing a domain name. (All automated by APIs and MCPs) They automatically create several rounds of app UI revisions. When I wake up, there are projects waiting for me to review: approve this design, give feedback, send that one back for improvement. Projects are actively coded and tested by the agents, while the entire process is tracked and logged (with "worker documents" that travel each step of the way, like a real factory.)

Benjamin De Kraker

481,750 次观看 • 8 个月前

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

Pratham

33,920 次观看 • 7 个月前

Automated Driving Testing System now live at Aravalli RTO * No more manual interference: The entire driving test is now AI-powered and automated. * Video analytics and real-time data ensure fair, fast, and accurate results. * Every move during the test is recorded, making the process fully transparent. * Instant evaluation means no long waits for results. * Helps eliminate bias, human error, and guesswork from the testing process. * Builds public trust in how driving licenses are issued. * Aravalli becomes the first RTO in the state to adopt this system setting standard for other RTOs * A step forward in making public services smarter, faster, and more reliable.

Automated Driving Testing System now live at Aravalli RTO * No more manual interference: The entire driving test is now AI-powered and automated. * Video analytics and real-time data ensure fair, fast, and accurate results. * Every move during the test is recorded, making the process fully transparent. * Instant evaluation means no long waits for results. * Helps eliminate bias, human error, and guesswork from the testing process. * Builds public trust in how driving licenses are issued. * Aravalli becomes the first RTO in the state to adopt this system setting standard for other RTOs * A step forward in making public services smarter, faster, and more reliable.

Harsh Sanghavi

26,769 次观看 • 1 年前

Giga Texas is building a new structure on the south end of the crash testing facility ... what is it for? It is a new Anthropomorphic Test Devices, or ATD, laboratory and is set to enhance Tesla's already world-class vehicle safety program, especially as the company gears up for the future of autonomous mobility. So, what exactly is an ATD? Anthropomorphic Test Devices, commonly known as crash test dummies, are sophisticated human surrogates equipped with hundreds of sensors like accelerometers and load cells. They simulate human responses—accelerations, forces, and deflections—during crashes, helping evaluate injury risks from frontal, side, or rollover impacts. Key types include the 50th percentile male—the most common—and the 5th percentile female, along with child sizes. But Tesla is pushing boundaries with advanced models like THOR, which stands for Test Device for Human Occupant Restraint. Developed by NHTSA, THOR offers superior biofidelity with over 150 sensors in newer models, capturing detailed data on brain, rib, and organ injuries.

Giga Texas is building a new structure on the south end of the crash testing facility ... what is it for? It is a new Anthropomorphic Test Devices, or ATD, laboratory and is set to enhance Tesla's already world-class vehicle safety program, especially as the company gears up for the future of autonomous mobility. So, what exactly is an ATD? Anthropomorphic Test Devices, commonly known as crash test dummies, are sophisticated human surrogates equipped with hundreds of sensors like accelerometers and load cells. They simulate human responses—accelerations, forces, and deflections—during crashes, helping evaluate injury risks from frontal, side, or rollover impacts. Key types include the 50th percentile male—the most common—and the 5th percentile female, along with child sizes. But Tesla is pushing boundaries with advanced models like THOR, which stands for Test Device for Human Occupant Restraint. Developed by NHTSA, THOR offers superior biofidelity with over 150 sensors in newer models, capturing detailed data on brain, rib, and organ injuries.

Joe Tegtmeyer 🚀 🤠🛸😎

19,326 次观看 • 7 个月前

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

James Sun

148,526 次观看 • 4 个月前

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

nader dabit

146,356 次观看 • 1 个月前

In 16 minutes we vibe coded a Web App and a Mobile App.... That share a backend Using Claude Code inside the Without writing a single line of code. App we built: instagram, except all the other users are AI agents that can post, like and comment. 00:00 Introduction 00:33 Starting with the Web App 01:08 First Prompt and Initial Setup 01:43 Authentication Process 02:49 Adding APIs and Enhancements 03:59 Testing the Web App 05:04 Redesigning the Web App 05:59 The Importance of Understanding Databases 07:20 Adding AI Agents 08:44 Setting Up the Admin Panel 10:02 Speeding Up Time for Testing 11:14 Finalizing the Web App 13:24 Building the Mobile App 16:11 Final Thoughts

In 16 minutes we vibe coded a Web App and a Mobile App.... That share a backend Using Claude Code inside the Without writing a single line of code. App we built: instagram, except all the other users are AI agents that can post, like and comment. 00:00 Introduction 00:33 Starting with the Web App 01:08 First Prompt and Initial Setup 01:43 Authentication Process 02:49 Adding APIs and Enhancements 03:59 Testing the Web App 05:04 Redesigning the Web App 05:59 The Importance of Understanding Databases 07:20 Adding AI Agents 08:44 Setting Up the Admin Panel 10:02 Speeding Up Time for Testing 11:14 Finalizing the Web App 13:24 Building the Mobile App 16:11 Final Thoughts

Riley Brown

68,207 次观看 • 7 个月前

just dropped a 24-min walkthrough showing how I turn raw n8n automations into actual front-end apps that your team can use no clunky JSON files, no ugly interfaces, and no dev team required I built a clean UI for one of my n8n flows - start to finish - all in one session it’s not a polished SaaS - but it is a working MVP you can test, share, or hand off step-by-step: – mapped the UX in ChatGPT – built the UI live in Bolt – connected it to the backend automation by the end, I had a usable internal tool that felt like a real product — all without writing a single line of frontend code if you're building powerful automations but not wrapping them in UI… you’re missing half the value also dropped my full prompt stack for planning and generating UIs with Claude or ChatGPT want the prompts? comment “UI”, follow + repost and I’ll send them over (must be following so I can DM)

just dropped a 24-min walkthrough showing how I turn raw n8n automations into actual front-end apps that your team can use no clunky JSON files, no ugly interfaces, and no dev team required I built a clean UI for one of my n8n flows - start to finish - all in one session it’s not a polished SaaS - but it is a working MVP you can test, share, or hand off step-by-step: – mapped the UX in ChatGPT – built the UI live in Bolt – connected it to the backend automation by the end, I had a usable internal tool that felt like a real product — all without writing a single line of frontend code if you're building powerful automations but not wrapping them in UI… you’re missing half the value also dropped my full prompt stack for planning and generating UIs with Claude or ChatGPT want the prompts? comment “UI”, follow + repost and I’ll send them over (must be following so I can DM)

J.B.

58,269 次观看 • 1 年前

Open Beta testing will commence soon, we have a small group of testers for now so just wait and I’ll reach out , but the people’s trading terminal is nearly done. The launcher is also done, you can see it on the left. We are going to make some upgrades to the Ui, and UX and remove some of those messages you see in the video, those are mostly for testing. And scale the speed and such but yeah core functionality is pretty good. We have been testing on main-net (sol) already so we are nearly good to go. It’s all built in rust so it’s fast and scalable. With Mobile first UI/UX also so you can ape like axiom but do it while taking a 💩.

Open Beta testing will commence soon, we have a small group of testers for now so just wait and I’ll reach out , but the people’s trading terminal is nearly done. The launcher is also done, you can see it on the left. We are going to make some upgrades to the Ui, and UX and remove some of those messages you see in the video, those are mostly for testing. And scale the speed and such but yeah core functionality is pretty good. We have been testing on main-net (sol) already so we are nearly good to go. It’s all built in rust so it’s fast and scalable. With Mobile first UI/UX also so you can ape like axiom but do it while taking a 💩.

Skely

20,941 次观看 • 9 个月前

I've been testing Bot Mode in the Hermes Desktop App a bit today, so I made a quick video showing the key features and how it differs from a normal Hermes session: - Side bar shows a list of bots (agent profiles) you can talk to - Agent Inbox allows bots to communicate directly with one another - Create Agent to make a new bot with a custom PFP, description, and configuration - Cron jobs bar on the right to create crons for specific bots Still in testing for the next day, so let's test it out and see how it can be improved!

I've been testing Bot Mode in the Hermes Desktop App a bit today, so I made a quick video showing the key features and how it differs from a normal Hermes session: - Side bar shows a list of bots (agent profiles) you can talk to - Agent Inbox allows bots to communicate directly with one another - Create Agent to make a new bot with a custom PFP, description, and configuration - Cron jobs bar on the right to create crons for specific bots Still in testing for the next day, so let's test it out and see how it can be improved!

tonbi

107,089 次观看 • 1 个月前

Simple mental model for cloud agents: clone the exact state of your laptop, multiply it infinitely, and make it accessible via HTTP. Most people still don't know cloud agents can spin up full Linux, Windows, Android, etc.. environments on demand, run computer-use tests, record annotated video proof of your app working through updates, drive Playwright against live Chrome with persistent auth, all triggerable from anywhere. Here I'm experimenting with a fork of Nous Research Hermes Agent built specifically on low latency. I've set up a Devin automation that checks Hermes daily for upstream changes, implements the updates, runs tests to make sure it works, sends me proof that it does, creates a PR, and reviews it. All I have to do to keep the fork up to date is review the daily morning PR.

Simple mental model for cloud agents: clone the exact state of your laptop, multiply it infinitely, and make it accessible via HTTP. Most people still don't know cloud agents can spin up full Linux, Windows, Android, etc.. environments on demand, run computer-use tests, record annotated video proof of your app working through updates, drive Playwright against live Chrome with persistent auth, all triggerable from anywhere. Here I'm experimenting with a fork of Nous Research Hermes Agent built specifically on low latency. I've set up a Devin automation that checks Hermes daily for upstream changes, implements the updates, runs tests to make sure it works, sends me proof that it does, creates a PR, and reviews it. All I have to do to keep the fork up to date is review the daily morning PR.

nader dabit

122,370 次观看 • 1 个月前

Testing continues to progress on the new UI / UX in the StackR marketplace and buying / selling of VeVe | Digital Collectibles using $OMI has never been easier or more enjoyable! Community Challenge: 1) List 1 eligible comic / collectible on for 2,000-5,000 OMI to familiarize yourself with the market and test the listing process (pick an item that trades for $1-$2 on VeVe, don’t use something expensive!) 2) Buy 1 listing from the marketplace in the 2,000-5,000 OMI range and relist the item for the same amount that you purchased it for to test the buying process and allow the previous user to buy their item back if they wish. The successful testing of the marketplace is crucial in allowing for a further expansion of items available for users- the more testing we can do now, the better the final product will be for all. If you want to participate but don’t have any OMI in your wallet, list the collectible and tag myself and Puddin Cheeks ⭕️ and we will buy your item so you can start to buy and participate in the ecosystem. We can’t wait to hear what you think and welcome all feedback to your experience on the marketplace! The future is bright 💙⭕️

Testing continues to progress on the new UI / UX in the StackR marketplace and buying / selling of VeVe | Digital Collectibles using $OMI has never been easier or more enjoyable! Community Challenge: 1) List 1 eligible comic / collectible on for 2,000-5,000 OMI to familiarize yourself with the market and test the listing process (pick an item that trades for $1-$2 on VeVe, don’t use something expensive!) 2) Buy 1 listing from the marketplace in the 2,000-5,000 OMI range and relist the item for the same amount that you purchased it for to test the buying process and allow the previous user to buy their item back if they wish. The successful testing of the marketplace is crucial in allowing for a further expansion of items available for users- the more testing we can do now, the better the final product will be for all. If you want to participate but don’t have any OMI in your wallet, list the collectible and tag myself and Puddin Cheeks ⭕️ and we will buy your item so you can start to buy and participate in the ecosystem. We can’t wait to hear what you think and welcome all feedback to your experience on the marketplace! The future is bright 💙⭕️

Foster Hilt ⭕️

23,700 次观看 • 1 年前

Testing Seedance 2.5 with an intense monster chase sequence. Generating a 30-second video with synchronized audio in a single pass already feels like a big step forward. What impressed me most is the consistency—visual style, characters, and environments stay coherent, making it much easier to extend a story across multiple scenes. The only downside is that I could only test it in 720p for now. Looking forward to seeing what it can do at higher resolutions. Really excited to build more cinematic projects with this model. This feels like an important milestone for AI video creation. Created with Seedance 2.5 by CapCut CapCut Viet Nam #CapCut #capcutcpp #capcutseedance25

Testing Seedance 2.5 with an intense monster chase sequence. Generating a 30-second video with synchronized audio in a single pass already feels like a big step forward. What impressed me most is the consistency—visual style, characters, and environments stay coherent, making it much easier to extend a story across multiple scenes. The only downside is that I could only test it in 720p for now. Looking forward to seeing what it can do at higher resolutions. Really excited to build more cinematic projects with this model. This feels like an important milestone for AI video creation. Created with Seedance 2.5 by CapCut CapCut Viet Nam #CapCut #capcutcpp #capcutseedance25

Min Story Lab

24,673 次观看 • 1 个月前

STi Testing In The Swingers Lifestyle Where to get comprehensive testing? If you're in the USA, we suggest ShamelessCare They've just lowered the price of a comprehensive STI panel from $409 to $369. With our $30 code, you can get it for $339 What's a comprehensive test include? ✔️Chlamydia oral throat swab test ✔️Chlamydia genital urine test ✔️Gonorrhea oral throat swab test ✔️Gonorrhea genital urine test ✔️Mycoplasma Genitalium urine test ✔️Trichomoniasis urine test ✔️Syphilis blood test ✔️HIV blood test ✔️Herpes Simplex 2 blood test ✔️Hepatitis B blood test ✔️Hepatitis C blood test Learn more Not many physicians offer such comprehensive testing. Studies show that fewer than 3% are screened for mycoplasma genitalium, which is often mistaken for recurrent BV by many women It's surprising how many of these tests come back positive. By raising awareness about these infections, you're making a significant impact on the lifestyle health #KnowYourStatus

STi Testing In The Swingers Lifestyle Where to get comprehensive testing? If you're in the USA, we suggest ShamelessCare They've just lowered the price of a comprehensive STI panel from $409 to $369. With our $30 code, you can get it for $339 What's a comprehensive test include? ✔️Chlamydia oral throat swab test ✔️Chlamydia genital urine test ✔️Gonorrhea oral throat swab test ✔️Gonorrhea genital urine test ✔️Mycoplasma Genitalium urine test ✔️Trichomoniasis urine test ✔️Syphilis blood test ✔️HIV blood test ✔️Herpes Simplex 2 blood test ✔️Hepatitis B blood test ✔️Hepatitis C blood test Learn more Not many physicians offer such comprehensive testing. Studies show that fewer than 3% are screened for mycoplasma genitalium, which is often mistaken for recurrent BV by many women It's surprising how many of these tests come back positive. By raising awareness about these infections, you're making a significant impact on the lifestyle health #KnowYourStatus

Wanderlust Swingers

18,998 次观看 • 3 年前