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。

✨ TryOnClothesAI 👕 new #buildinpublic AI app: 1. Upload clothes 2. Upload model (yourself) 3. Generate preview alpha version but a simple working prototype. very excited about this project! 👇🏻Watch quick demo 👇🏻

Timon Wong

7,096 subscribers

38,692 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

ernest 的头像

ernest3 年前

WardrobeAI

Tim Wong 的头像

Tim Wong3 年前

That’s a good name. I might use that if the domain is available. 🤣

Ryan Badger 的头像

Ryan Badger3 年前

Pretty cool! What engine/API are you using to generate the images?

Tim Wong 的头像

Tim Wong3 年前

Created my own model

Yifan Goh 的头像

Yifan Goh3 年前

Sick shipping speed, Tim ⚡️ Can’t wait for the launch 🚀

Tim Wong 的头像

Tim Wong3 年前

Thanks senpai. Working hard to get it to even beta first. It barely works now 🤣

Josh Miller 的头像

Josh Miller3 年前

Wow, impressive. I pity clothe models 😅

Upen 的头像

Upen3 年前

Are you kidding 🤯

Mei 🌻 的头像

Mei 🌻3 年前

Oh my gosh this is so cool! Go Tim! 🤯

Tim Wong 的头像

Tim Wong3 年前

Thanks Mei 😇

相关视频

Stop wasting hours filming b-rolls! Introducing 👋 Get high-quality, professional clips of yourself in 3 simple steps: 1. Upload photos 2. Pick a cinematic scene 3. Generate clip All in under 3 minutes! Watch demo below 👇

Stop wasting hours filming b-rolls! Introducing 👋 Get high-quality, professional clips of yourself in 3 simple steps: 1. Upload photos 2. Pick a cinematic scene 3. Generate clip All in under 3 minutes! Watch demo below 👇

Florin Pop 👨🏻‍💻

32,512 次观看 • 7 个月前

It's been a while since I submitted a Chrome extension, but once it's approved I'll share. You can: 1) Add you own Replicate API key 2) Upload an image of yourself 3) Right click any image to try on the clothes Thanks for all the feedback. #buildinpublic

It's been a while since I submitted a Chrome extension, but once it's approved I'll share. You can: 1) Add you own Replicate API key 2) Upload an image of yourself 3) Right click any image to try on the clothes Thanks for all the feedback. #buildinpublic

Aaron

40,004 次观看 • 2 年前

Skip the boilerplate and create entire apps from scratch with the AI-powered New Project flow, available in Android Studio Panda 2 → Describe your vision, upload style inspiration, and watch the agent generate a detailed plan and first draft of your app.

Skip the boilerplate and create entire apps from scratch with the AI-powered New Project flow, available in Android Studio Panda 2 → Describe your vision, upload style inspiration, and watch the agent generate a detailed plan and first draft of your app.

Android Studio

13,593 次观看 • 6 个月前

Swap yourself into anyone, change backgrounds, or recreate viral effects with just ONE photo using the Seedance 2.5 model. Here's how it works: 1. Upload your reference video 2. Drop in photos of the elements you want to swap 3. Type a simple prompt 4. Click "Generate"

Swap yourself into anyone, change backgrounds, or recreate viral effects with just ONE photo using the Seedance 2.5 model. Here's how it works: 1. Upload your reference video 2. Drop in photos of the elements you want to swap 3. Type a simple prompt 4. Click "Generate"

Higgsfield AI 🧩

34,931 次观看 • 7 天前

$A 20-year-old Chinese guy turned himself into an AI girl and claims it made him $8,240. The free guide is stupid simple. WAN2.2 lets him record one normal video, upload one character photo, and replace his whole body while keeping the same motion. 1. open Tongyi Wanxiang 2. Digital Human 3. Character Replacement 4. upload your clip 5. upload the girl photo 6. Professional mode 7. Generate Same script. Same hands. New face. Endless product videos. Sa\/e this before every guy on Tiktok becomes a skincare girl.$

A 20-year-old Chinese guy turned himself into an AI girl and claims it made him $8,240. The free guide is stupid simple. WAN2.2 lets him record one normal video, upload one character photo, and replace his whole body while keeping the same motion. 1. open Tongyi Wanxiang 2. Digital Human 3. Character Replacement 4. upload your clip 5. upload the girl photo 6. Professional mode 7. Generate Same script. Same hands. New face. Endless product videos. Sa\/e this before every guy on Tiktok becomes a skincare girl.

0xTria

17,465 次观看 • 2 个月前

✨ New highly requested feature You can now do [ 🗂️ Batch try on ] and [ 🗂️ Batch remix ] on Photo AI Upload 100s of different clothing items you have (even laid flat) and Photo AI will batch generate images of them with your AI model wearing it Nice if you have a big catalog of clothes for your shop you want to put on a model You can also batch remix meaning upload 100s of photos you want to imitate (like poses, looks, styles) but with your AI model and it will run them automatically and take a photo for each I'm slowly adding these kinds of features to make Photo AI more usable for B2B purposes like this 😊

✨ New highly requested feature You can now do [ 🗂️ Batch try on ] and [ 🗂️ Batch remix ] on Photo AI Upload 100s of different clothing items you have (even laid flat) and Photo AI will batch generate images of them with your AI model wearing it Nice if you have a big catalog of clothes for your shop you want to put on a model You can also batch remix meaning upload 100s of photos you want to imitate (like poses, looks, styles) but with your AI model and it will run them automatically and take a photo for each I'm slowly adding these kinds of features to make Photo AI more usable for B2B purposes like this 😊

@levelsio

136,015 次观看 • 1 年前

Want to try a new haircut? Check out this AI workflow: 1. upload a selfie & prompt your desired haircut 2. uses Nano Banana to generate your haircut 3. then Kling 2.1 morphs from old you to new you 4. Claude helping behind the scenes with all the prompts link to glif below 👇

Want to try a new haircut? Check out this AI workflow: 1. upload a selfie & prompt your desired haircut 2. uses Nano Banana to generate your haircut 3. then Kling 2.1 morphs from old you to new you 4. Claude helping behind the scenes with all the prompts link to glif below 👇

fabian

809,440 次观看 • 1 年前

I built a money printer 🤯 Imagine listing items once and having an AI sales agent handle EVERYTHING else. That's what i built this weekend ✨ 1. Upload a photo of your item 2. AI analyzes brand, model & condition 3. Research prices across Facebook & Amazon 4. AI agent takes over: ◆ Answers buyer questions instantly ◆ Counters lowball offers intelligently ◆ Closes the deals at your target price ◆ You just ship the item You literally just: → Take photo → Ship item → Get paid This This project is 100% free and Open Source. I built this to test out AI agents Tech Stack: Vercel AI SDK shadcn Prisma Postgres #buildinpublic #opensource

CodeHagen

95,960 次观看 • 1 年前

Creating engaging business content is simple using Flow. Try this workflow for yourself 👇 1. Interrupt the scroll: Use a descriptive text prompt with eye-catching movement. 2. Play with perspective: Generate engaging angles of your environment. Try prompting for macro shots. 3. Brand spotlight: Upload real product images using Ingredients to Video. 4. Show us what you create! ☕️

Flow by Google

15,746 次观看 • 7 个月前

In case you missed it... we dropped 5 HUGE updates this week 🔥 1. Voice Isolation – Remove background noise and get clear audio in seconds. 2. Voice Changer – Upload a voice or use cloned/custom voices and transform them instantly. 3. Voice Design – Generate unique voices from a simple text prompt. 4. AI Creative Assistant – Generate, translate, and enhance scripts faster. 5. 12-Minute Generations - Generate up to 12 minutes of content. All these features are live now—don’t wait, try them today!

In case you missed it... we dropped 5 HUGE updates this week 🔥 1. Voice Isolation – Remove background noise and get clear audio in seconds. 2. Voice Changer – Upload a voice or use cloned/custom voices and transform them instantly. 3. Voice Design – Generate unique voices from a simple text prompt. 4. AI Creative Assistant – Generate, translate, and enhance scripts faster. 5. 12-Minute Generations - Generate up to 12 minutes of content. All these features are live now—don’t wait, try them today!

Hedra

72,797 次观看 • 1 年前

Data Models - Better AI Code in 5 Minutes Your AI isn't consistent because you're missing one file. I had the same problem until I started using a data model file. In this video, I'm showing you the exact two prompts I use: one generates the data model, the second uses it to generate features without breaking my app. Testing this with AnimeLeak (my actual production app) adding an admin approval feature. Using Droid with Sonnet 4.5 in spec mode, but this works in Cursor, Claude, or whatever you're using. KEY TIMESTAMPS 00:00 - The One File Your AI is Missing 00:44 - Prompt 1: Generate a Data Model 01:12 - The Result: Data Model Documentation 02:12 - Prompt 2: Implement a New Feature 03:00 - Reviewing the AI-Generated Spec 04:17 - Why This Workflow is So Powerful 04:32 - Your 3-Step Action Plan 05:12 - Next Video: Live Code Generation

Data Models - Better AI Code in 5 Minutes Your AI isn't consistent because you're missing one file. I had the same problem until I started using a data model file. In this video, I'm showing you the exact two prompts I use: one generates the data model, the second uses it to generate features without breaking my app. Testing this with AnimeLeak (my actual production app) adding an admin approval feature. Using Droid with Sonnet 4.5 in spec mode, but this works in Cursor, Claude, or whatever you're using. KEY TIMESTAMPS 00:00 - The One File Your AI is Missing 00:44 - Prompt 1: Generate a Data Model 01:12 - The Result: Data Model Documentation 02:12 - Prompt 2: Implement a New Feature 03:00 - Reviewing the AI-Generated Spec 04:17 - Why This Workflow is So Powerful 04:32 - Your 3-Step Action Plan 05:12 - Next Video: Live Code Generation

Ray Fernando

15,479 次观看 • 10 个月前

Bro to Bro : Make I cast this update fast fast. This guy swapped his face to any celebrity but didn’t share the tool Here is the tool , steps and prompt : Site : openart.)ai Steps : •Sign Up •Go to Video Mode: On the main dashboard, click the Video tab (highlighted in green in your screenshot). •Step 2: Set Up Your Project >Select "Modify Video": Make sure the green button labeled Modify Video is active. This is the mode that keeps the original video's motion while changing the details. >Pick the Model: In the dropdown menu, ensure Kling 01 is selected. This is currently the best model for keeping movements "exactly" the same. •Step 3: Upload Your video 1. Upload the "your" Video: Click box #1 (Upload Video to Edit) and select the video of the person talking. • Tip: Keep the video between 3 and 10 seconds. 2. Upload the "New Face": Click box #2 (Reference Image) and upload a clear photo of the face you want to use. • Tip: Use an image where the face is looking forward and well-lit Replace the face in this video with the person This is the prompt he used though : "Face swap the input photo of a young Black man in a beige cap and black t-shirt onto Keanu Reeves: long dark hair, beard, serious expression, gray shirt, indoor setting. High detail, realistic lighting, seamless blend. For Tyla: Swap to South African singer Tyla, braided hair, light blue top, expressive pose. For Billie Eilish: Green-black hair, casual black shirt, pouting expression."

Bro to Bro : Make I cast this update fast fast. This guy swapped his face to any celebrity but didn’t share the tool Here is the tool , steps and prompt : Site : openart.)ai Steps : •Sign Up •Go to Video Mode: On the main dashboard, click the Video tab (highlighted in green in your screenshot). •Step 2: Set Up Your Project >Select "Modify Video": Make sure the green button labeled Modify Video is active. This is the mode that keeps the original video's motion while changing the details. >Pick the Model: In the dropdown menu, ensure Kling 01 is selected. This is currently the best model for keeping movements "exactly" the same. •Step 3: Upload Your video 1. Upload the "your" Video: Click box #1 (Upload Video to Edit) and select the video of the person talking. • Tip: Keep the video between 3 and 10 seconds. 2. Upload the "New Face": Click box #2 (Reference Image) and upload a clear photo of the face you want to use. • Tip: Use an image where the face is looking forward and well-lit Replace the face in this video with the person This is the prompt he used though : "Face swap the input photo of a young Black man in a beige cap and black t-shirt onto Keanu Reeves: long dark hair, beard, serious expression, gray shirt, indoor setting. High detail, realistic lighting, seamless blend. For Tyla: Swap to South African singer Tyla, braided hair, light blue top, expressive pose. For Billie Eilish: Green-black hair, casual black shirt, pouting expression."

Kenn_eth

134,119 次观看 • 1 天前

$We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:$

We’re shipping two major updates to streamline your creative workflow, allowing you to generate high-speed images with one model and then instantly animate them with the other—all at a fraction of the cost 🍌⚡️ 1️⃣ Introducing Nano Banana 2 Lite: Our fastest and most cost-efficient Gemini Image model yet delivers text-to-image outputs in under 4 seconds. Now available via the Gemini API and Google AI Studio, and rolling out soon across @NotebookLM, Google Flow, Google Gemini, Stitch by Google, Google Search and Google Photos. 2️⃣ Gemini Omni Flash in Public Preview: Our natively multimodal model for cost-efficient video generation and conversational editing. Now available via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform so you can integrate the model into your workflow. While exciting on their own, the real magic happens when you build using these models together. Watch how our interior design demo integrates Nano Banana 2 Lite and Omni to instantly reimagine any space. Upload a photo, swipe through tailored design concepts, and see Omni bring the details to life in cinematic motion. Try out the demo app in AI Studio:

Google AI

129,052 次观看 • 2 个月前

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,078,824 次观看 • 3 个月前

✨ New [ 👗 Try On 2.0 ] on Finally it works REALLY WELL: - pick any clothing, from a screenshot or laid out photo, upload it - click take photo, you can prompt the location of model, light (sunset), time, anything like normal etc. - AI model will wear the clothes you uploaded - textured prints now work REALLY well too, not perfect, but very close - it drapes almost any clothes properly to the body now, still buggy photos but 60-80% is good enough I think it's good enough for Shopify sellers now cc tobi lutke, if anyone here has clothes they want me to try on Photo AI's models, reply a pic and I'll render them and reply to you You can take 1000 pics for $39/mo on Photo AI so it's very economical ~$0.04 per photo, with error ratio maybe $0.06 per good photo you can use for your store without having to do a model photo shoot anymore Render time is about 1-2 minutes per photo but you can run them in parallel of course Last year try on mode wasn't precise enough and it couldn't do textures well, it would detect the clothes, prompt for them, and use the photo as ControlNet reference but that didn't actually work so well as people made it out to be, now it's 1000x better and actually works Nothing is perfect of course, but I'm trying!

✨ New [ 👗 Try On 2.0 ] on Finally it works REALLY WELL: - pick any clothing, from a screenshot or laid out photo, upload it - click take photo, you can prompt the location of model, light (sunset), time, anything like normal etc. - AI model will wear the clothes you uploaded - textured prints now work REALLY well too, not perfect, but very close - it drapes almost any clothes properly to the body now, still buggy photos but 60-80% is good enough I think it's good enough for Shopify sellers now cc tobi lutke, if anyone here has clothes they want me to try on Photo AI's models, reply a pic and I'll render them and reply to you You can take 1000 pics for $39/mo on Photo AI so it's very economical ~$0.04 per photo, with error ratio maybe $0.06 per good photo you can use for your store without having to do a model photo shoot anymore Render time is about 1-2 minutes per photo but you can run them in parallel of course Last year try on mode wasn't precise enough and it couldn't do textures well, it would detect the clothes, prompt for them, and use the photo as ControlNet reference but that didn't actually work so well as people made it out to be, now it's 1000x better and actually works Nothing is perfect of course, but I'm trying!

@levelsio

728,514 次观看 • 2 年前