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.

Facefusion 3.0 is here! The 100% open source face swap app powered by Gradio, launched v3.0, supporting all kinds of new features including: - Age Modifier - Face Editor (via LivePortrait) - Workflows! (Job Queue System) - And more

cocktail peanut

32,917 subscribers

103,597 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

cocktail peanut1 year ago

You can install with one click via

cocktail peanut1 year ago

1. Face Editor (LivePortrait) This is so cool. Incorporate realtime face editing right into the face swap workflow. Just select "face_editor" on the left column and experiment with various expressions, and they will be incorporated in the result video!

cocktail peanut1 year ago

2. Age Editor You can also modify the face age, making the face younger or older. Here's a face swap of Arnold Schwarzenegger into three female faces, WHILE making the age younger and older. You can see the difference between the two!

cocktail peanut1 year ago

3. Workflows Facefusion now has WORKFLOWS (called "jobs"). Stack as many jobs as you want, for example swap one face, pass it the next step that swaps another face, and pass to next step where it changes age. Here's a great intro from @kriebe

cocktail peanut1 year ago

Here's the Github for Facefusion, go star the project, and join their community

cocktail peanut1 year ago

Also, I recommend checking out all the Facefusion related videos on @kriebe's channel to learn to use it properly.

Uncanny Harry AI1 year ago

You are a star Brother 👊

cocktail peanut1 year ago

thank you!👊

Blaine Brown1 year ago

LFG! 🫶🔥

Ago-ra@AI1 year ago

🤣🤣🤣

Related Videos

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!

🤯 You can now easily face-swap any video, all locally on your Macbook. All you need is a photo and a video. FaceFusion is an open-source face swapper/enhancer with a simple web interface. On an M1/M2 Macbook, it even makes use of Core ML!

Marcel Pociot 🧪

206,509 views • 3 years ago

$SuperSplat Editor 3.0 is here 🚀 The free and open source Gaussian splat editor has been rebuilt from the ground up on WebGPU. Far larger scenes, a fraction of the memory, smooth on tens of millions of Gaussians. Try it now → 🧵 What's new...$

SuperSplat Editor 3.0 is here 🚀 The free and open source Gaussian splat editor has been rebuilt from the ground up on WebGPU. Far larger scenes, a fraction of the memory, smooth on tens of millions of Gaussians. Try it now → 🧵 What's new...

PlayCanvas

32,755 views • 3 days ago

A new version of the AssetDash is app is available - update now! ✨ and it has a number of special features including: - Premium Whale Watch Feeds - Aggregated Whale Watch Leaderboards All powered by Moby and unlocked by $MOBY ownership or your AssetDash trade activity. Let's dive into all of it 👇

A new version of the AssetDash is app is available - update now! ✨ and it has a number of special features including: - Premium Whale Watch Feeds - Aggregated Whale Watch Leaderboards All powered by Moby and unlocked by $MOBY ownership or your AssetDash trade activity. Let's dive into all of it 👇

AssetDash

399,090 views • 1 year ago

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

Andrew Ng

224,608 views • 2 years ago

Alchemists, we have an exciting announcement: The Enchanted Garden 2.0 Update is now available! It's full of new features and changes, including garden updates, a new talent system, the introduction of game difficulties, and MORE! Read more here:

Alchemists, we have an exciting announcement: The Enchanted Garden 2.0 Update is now available! It's full of new features and changes, including garden updates, a new talent system, the introduction of game difficulties, and MORE! Read more here:

Potion Craft - Alchemist Simulator

52,843 views • 1 year ago

Akool’s Face Swap page just got a major upgrade. Now, all swap features are fully integrated into one powerful workflow — including Face Swap, Character Swap, and Head Swap. Whether you want to create content from existing assets or build something completely new based on your creative vision, Akool gives you the flexibility to do it all in one place. With studio-level face swap quality, your content will look more realistic, cinematic, and professional than ever before. From social content to commercial production, create visuals that truly stand out. One platform. Endless possibilities. Only on Akool.

Akool’s Face Swap page just got a major upgrade. Now, all swap features are fully integrated into one powerful workflow — including Face Swap, Character Swap, and Head Swap. Whether you want to create content from existing assets or build something completely new based on your creative vision, Akool gives you the flexibility to do it all in one place. With studio-level face swap quality, your content will look more realistic, cinematic, and professional than ever before. From social content to commercial production, create visuals that truly stand out. One platform. Endless possibilities. Only on Akool.

Akool Inc

1,874,286 views • 3 months ago

This face swap is insane and I will give you two ways if you have the right laptop & tools Step 1: Get the tool Download a real-time face swap app like Deep-Live-Cam, DeepFaceLive, or Swapface (PC works best. A good GPU = better results.) Step 2: Pick ONE face Use a clear, front-facing photo of the face you want to appear as. Good lighting = more realism. Step 3: Start the live swap Open the app Turn on your webcam Load the photo You’ll see the face swap happen in real time. Step 4: Enable virtual camera Turn on “Virtual Cam” or “Stream Output” inside the tool. Step 5: Join a video call Open Zoom / Discord / FaceTime Select the tool as your camera Your movements and expressions sync live.

This face swap is insane and I will give you two ways if you have the right laptop & tools Step 1: Get the tool Download a real-time face swap app like Deep-Live-Cam, DeepFaceLive, or Swapface (PC works best. A good GPU = better results.) Step 2: Pick ONE face Use a clear, front-facing photo of the face you want to appear as. Good lighting = more realism. Step 3: Start the live swap Open the app Turn on your webcam Load the photo You’ll see the face swap happen in real time. Step 4: Enable virtual camera Turn on “Virtual Cam” or “Stream Output” inside the tool. Step 5: Join a video call Open Zoom / Discord / FaceTime Select the tool as your camera Your movements and expressions sync live.

Wilsxn

265,203 views • 8 months ago

Open-Source Robotic Hand That Costs Just $300. California-based company TetherIA.ai has officially launched its open-source robotic hand, the Aero Hand Open. Designed to be the most capable at the lowest cost, this hand is a new tool for embodied AI research. In the clip, it demonstrates impressive dexterity by grasping an M5 screw, picking up an iPhone, and opening a soda can. Key Features: ► Price: $314.00 ► Open Source: CAD, electronics, and firmware are all open source. ► Actuation: 7 Active Degrees of Freedom (16 joints) with a tendon-driven design. ► Weight: Under 400 grams. ► Purpose: Built for embodied AI research to make dexterous manipulation accessible to all. For more details and to purchase:

Open-Source Robotic Hand That Costs Just $300. California-based company TetherIA.ai has officially launched its open-source robotic hand, the Aero Hand Open. Designed to be the most capable at the lowest cost, this hand is a new tool for embodied AI research. In the clip, it demonstrates impressive dexterity by grasping an M5 screw, picking up an iPhone, and opening a soda can. Key Features: ► Price: $314.00 ► Open Source: CAD, electronics, and firmware are all open source. ► Actuation: 7 Active Degrees of Freedom (16 joints) with a tendon-driven design. ► Weight: Under 400 grams. ► Purpose: Built for embodied AI research to make dexterous manipulation accessible to all. For more details and to purchase:

RoboHub🤖

45,830 views • 11 months ago

🚀 We're excited to announce the release of FuzzForge Open Source (OSS)! FuzzForge is our open-source platform designed to automate offensive security workflows & AI Agents, from static analysis to fuzzing, debugging, and root cause analysis, all with AI assistance. 🔷 Open-source release is the first step toward our vision of "Offensive-Security-as-Code." 🔷 Workflows you can run, share, and extend. 🔷 Built by the team at FuzzingLabs. Github : Join the Alpha Waitlist : We've also launched the FuzzingLabs Community Discord where researchers, engineers, and security enthusiasts can connect and collaborate: 👉 Come join us and Let's forge the future of AppSec & Offensive Security together! #FuzzForge #Fuzzing #AppSec #OpenSource #CyberSecurity

🚀 We're excited to announce the release of FuzzForge Open Source (OSS)! FuzzForge is our open-source platform designed to automate offensive security workflows & AI Agents, from static analysis to fuzzing, debugging, and root cause analysis, all with AI assistance. 🔷 Open-source release is the first step toward our vision of "Offensive-Security-as-Code." 🔷 Workflows you can run, share, and extend. 🔷 Built by the team at FuzzingLabs. Github : Join the Alpha Waitlist : We've also launched the FuzzingLabs Community Discord where researchers, engineers, and security enthusiasts can connect and collaborate: 👉 Come join us and Let's forge the future of AppSec & Offensive Security together! #FuzzForge #Fuzzing #AppSec #OpenSource #CyberSecurity

FuzzingLabs

11,156 views • 11 months ago

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

31,048 views • 11 months ago

A new era is born in the action-packed Jurassic World Evolution 3: Rebirth Expansion. Coming 16 June! Delve into a game expanding narrative inspired by the dramatic events of Jurassic World Rebirth. Take control of three top-secret locations and come face-to-face with four new dinosaurs, including the terrifying Distortus rex! Learn more:

A new era is born in the action-packed Jurassic World Evolution 3: Rebirth Expansion. Coming 16 June! Delve into a game expanding narrative inspired by the dramatic events of Jurassic World Rebirth. Take control of three top-secret locations and come face-to-face with four new dinosaurs, including the terrifying Distortus rex! Learn more:

Jurassic World Evolution 3

510,843 views • 3 months ago

At #HederaCon our CEO May Chan joined a powerhouse panel on Hiero & the future of open-source trust. When infrastructure is open & shared, innovation flourishes - builders, entrepreneurs, users and enterprises all benefit. By embracing Hiero’s open ecosystem, HashPack can introduce new features swiftly, harmonize with emerging standards and strengthen the entire Hedera network.

At #HederaCon our CEO May Chan joined a powerhouse panel on Hiero & the future of open-source trust. When infrastructure is open & shared, innovation flourishes - builders, entrepreneurs, users and enterprises all benefit. By embracing Hiero’s open ecosystem, HashPack can introduce new features swiftly, harmonize with emerging standards and strengthen the entire Hedera network.

HashPack Wallet

10,128 views • 3 months ago

The Fondant Easy Custom Normals addon v2.1.0 is here! Works in Blender 4.3-4.5. I've reworked the Laplacian Smooth Modifier to run on Face Corners, giving us more control and quad mesh support. Also optimizations and new features. No longer needs to run slow triangulation operations. Stability problems are addressed by Momentum Smoothing, which also allows the strength to be scaled up as high as 3 without blowing everything up. So you can do more smoothing in fewer iterations! And there's more control of how things interact with the smoothing. Instead of only choosing how strong it is on a given point, now you can scale the amount it contributes to the smoothing of its neighbors. Or reduce its Original Normal strength to allow it to be overwritten or filled in. These changes and more are all part of the free tier of the addon. Please consider picking up the paid Face Proxy system to support continued development!

The Fondant Easy Custom Normals addon v2.1.0 is here! Works in Blender 4.3-4.5. I've reworked the Laplacian Smooth Modifier to run on Face Corners, giving us more control and quad mesh support. Also optimizations and new features. No longer needs to run slow triangulation operations. Stability problems are addressed by Momentum Smoothing, which also allows the strength to be scaled up as high as 3 without blowing everything up. So you can do more smoothing in fewer iterations! And there's more control of how things interact with the smoothing. Instead of only choosing how strong it is on a given point, now you can scale the amount it contributes to the smoothing of its neighbors. Or reduce its Original Normal strength to allow it to be overwritten or filled in. These changes and more are all part of the free tier of the addon. Please consider picking up the paid Face Proxy system to support continued development!

aVersionOfReality

47,920 views • 1 year ago

Just launched #CES2026, the new open-source NVIDIA Nemotron Speech ASR model is here to solve latency drift and redundant compute. Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up to 3x more throughput on your GPU. 🤗 Read the technical blog with real-world results from Daily and Modal on Hugging Face:

Just launched #CES2026, the new open-source NVIDIA Nemotron Speech ASR model is here to solve latency drift and redundant compute. Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up to 3x more throughput on your GPU. 🤗 Read the technical blog with real-world results from Daily and Modal on Hugging Face:

NVIDIA AI Developer

138,518 views • 8 months ago

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 views • 1 month ago

Good afternoon you DeFi legends! 👇Slap this Space reminder for 9pmEST👇 We are hosting now our third Open Mic Night that is brought to you by the Every Launchpad and $Every token! If you have launched a project on then this is your golden ticket of exposure as we will be inviting all communities to present their launched project! This isn’t just a one time thing but long term strategic partnership with EDM that supports those in the ecosystem. If you didn’t launch on that’s ok we will also open the spaces to all of DeFi for a few projects as well because EDM is the people’s platform and is here to support everyone! The biggest gap we face in DeFi is the disconnect between pads and the people launching their projects. These launchpads continue to give bare minimum support and show they aren’t here for the culture and betterment of DeFi. So let’s take it back! It’s starts with supporting those who support us! is here for the people and the culture! Powered by xTrends #Sponsored #Ad

Good afternoon you DeFi legends! 👇Slap this Space reminder for 9pmEST👇 We are hosting now our third Open Mic Night that is brought to you by the Every Launchpad and $Every token! If you have launched a project on then this is your golden ticket of exposure as we will be inviting all communities to present their launched project! This isn’t just a one time thing but long term strategic partnership with EDM that supports those in the ecosystem. If you didn’t launch on that’s ok we will also open the spaces to all of DeFi for a few projects as well because EDM is the people’s platform and is here to support everyone! The biggest gap we face in DeFi is the disconnect between pads and the people launching their projects. These launchpads continue to give bare minimum support and show they aren’t here for the culture and betterment of DeFi. So let’s take it back! It’s starts with supporting those who support us! is here for the people and the culture! Powered by xTrends #Sponsored #Ad

K1d Crypt0

20,043 views • 8 months ago

sneak peek at our UGC face editor update coming Very soon -granular per eye, eyebrow etc adjustments including size, rotation and position -directional scaling -transparency support -layer ordering -pinning items -preset colors -(not shown) import images -- also supports all of the above all of these face features will also be supported in the item combo creator (more sneak peeks soon 👀) our focus remains on making powerful item creation as easy as possible, as always your creations can be uploaded to roblox!

sneak peek at our UGC face editor update coming Very soon -granular per eye, eyebrow etc adjustments including size, rotation and position -directional scaling -transparency support -layer ordering -pinning items -preset colors -(not shown) import images -- also supports all of the above all of these face features will also be supported in the item combo creator (more sneak peeks soon 👀) our focus remains on making powerful item creation as easy as possible, as always your creations can be uploaded to roblox!

WhoseTrade

25,889 views • 2 months ago

Introducing Live, 3D virtual townhall for ANY Pump.fun coin, powered by their brand new Coin Communities API & SDK. No more staring at charts in isolation. Custom 3D Avatars: Build yours on and drop straight in. • 100% Multiplayer: Meet face-to-face, hit emotes, and raid with the squad. • In-World Swaps: Watch the billboard pump live and execute Solana swaps directly inside the game. Never leave the trenches. The meta is shifting. Stop scrolling the timeline and meet your bags face-to-face. Try it live right now:

three.ws

41,899 views • 3 months ago

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code. Best of all, the tool is 100% free and open source. But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more. 📌 Subscribe to get our full tutorial tomorrow:

You can now make videos like this using HTML. I didn’t believe it at first until the HyperFrames team showed me how they do it directly in Codex and Claude Code. Best of all, the tool is 100% free and open source. But you need to learn the right workflows to make the videos look great - including generating a frame.md, storyboards, and more. 📌 Subscribe to get our full tutorial tomorrow:

Peter Yang

193,295 views • 2 months ago