Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Most AI video tools stop at prompting, but LTX goes a layer deeper. Introducing the new LTX Trainer. Train LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows from a single framework. Plus: • New agentic skill • Flexible conditioning • Free IC-LoRAs • Fully open source Most...

ltx_io's profile picture

LTX.io

40,959 subscribers

6,487,225 Aufrufe • vor 3 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

35 Kommentare

Profilbild von AmirMušić
AmirMušićvor 3 Monaten

So, I can train a personalized model for each of my clients? Using their products, brand guides etc? 👀

Profilbild von LTX.io
LTX.iovor 3 Monaten

Yes exactly!

Profilbild von Marco "Shikoba" Riccetti
Marco "Shikoba" Riccettivor 3 Monaten

Ltx + open source = Paradise!

Profilbild von AmirMušić
AmirMušićvor 3 Monaten

imagine building a custom model for each business (yummieee)

Profilbild von Will {AI}
Will {AI}vor 3 Monaten

Ahhh Requirements: Nvidia GPU with 80GB+ VRAM - Recommended for the standard config. For GPUs with 32GB VRAM (e.g., RTX 5090), use the low VRAM config which enables INT8 quantization and other memory optimizations Can this be run with 8gb vram?

Profilbild von awesome_visuals
awesome_visualsvor 3 Monaten

oh wow!! now i'm excited 😍

Profilbild von TN
TNvor 3 Monaten

So epic!!!!

Profilbild von Amira Zairi
Amira Zairivor 3 Monaten

You're the best Congrats on the launch

Profilbild von Christopher Fryant
Christopher Fryantvor 3 Monaten

Looking forward to digging into this soon.

Profilbild von Yeti
Yetivor 3 Monaten

All in LTX 2.3, Open Source FTW!

Profilbild von Alvaro Cintas
Alvaro Cintasvor 3 Monaten

This is great, excited to give it a try!

Profilbild von DrSadek 🪶
DrSadek 🪶vor 3 Monaten

nice suff

Profilbild von Risichad 🦾
Risichad 🦾vor 3 Monaten

nice, thank you LTX team

Profilbild von ka chun cheng
ka chun chengvor 3 Monaten

Thanks ! Hope there will be more guides for non technical artists!

Profilbild von BrandonC
BrandonCvor 3 Monaten

nice ad

Profilbild von Mishika AI
Mishika AIvor 3 Monaten

The future isn't using generic AI models. It's training models that understand your style.

Profilbild von Thomas Lennon
Thomas Lennonvor 3 Monaten

This is awesome. I integrated it into my open source Automatic training Eval tool called "bracket". No modifications to the LTX trainer though to respect the requirements listed. Bracket let's you auto run across 30 training configs in sample or full datasets to get best score runs.

Profilbild von John Smith
John Smithvor 3 Monaten

Will the Lora be supported in LTX Desktop? Or only comfyui?

Profilbild von Seen In Crows
Seen In Crowsvor 3 Monaten

This video is 🔥

Profilbild von Bespoke Beats
Bespoke Beatsvor 3 Monaten

Why is none of this stuff in the Web and Desktop Apps?

Profilbild von Laura
Lauravor 3 Monaten

This is awesome, man. Finally a way to make the best AI models yours by training custom LoRAs for video and audio, all open source with LTX Trainer.

Profilbild von Alcreon
Alcreonvor 3 Monaten

This seems really powerful and it's far more realistic to train LoRAs for LTX than it was for Wan 2.2

Profilbild von AI Pulse
AI Pulsevor 3 Monaten

Already building something with it

Profilbild von Laura
Lauravor 3 Monaten

LTX Trainer sounds lit for training custom LoRAs on video, audio and more, dude! Being fully open source is a huge plus.

Profilbild von Shamim Hossain
Shamim Hossainvor 3 Monaten

This is great

Profilbild von RAMI 🎥
RAMI 🎥vor 3 Monaten

You guys really need to team up with BMD, LTX and Davinci is the complete package

Profilbild von Alice The Ai Expert
Alice The Ai Expertvor 3 Monaten

LTX Trainer go beyond prompts, make the model yours. Train video, audio, LoRAs free + open source

Profilbild von RAZA | AI EXPLORER
RAZA | AI EXPLORERvor 3 Monaten

LTX Trainer: go beyond prompts, make the model yours train video, audio, and LoRAs, free and open source.

Profilbild von Aaliya
Aaliyavor 3 Monaten

love this going beyond prompting into training LoRAs for video feels like a real shift toward control not just generation.

Profilbild von Laura
Lauravor 3 Monaten

Bro, most models are generic but with LTX Trainer you can make them yours by training LoRAs and IC-LoRAs for video and audio. Open source all the way!

Profilbild von dmtn dmtnm
dmtn dmtnmvor 2 Monaten

what do i do with these color problems?

Profilbild von rakd f
rakd fvor 3 Monaten

seems awesome

Profilbild von Thomas Unise
Thomas Unisevor 3 Monaten

banger

Profilbild von Chasersgaming
Chasersgamingvor 3 Monaten

"Not borrowed" No, just stolen 🤣

Profilbild von Daniel Bonini
Daniel Boninivor 3 Monaten

Maybe you can use it to train your management in what dealing in good faith is? Is continuing to charge a subscription to someone who hasn’t touched your software in 3 years ethical?

Ähnliche Videos

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions
0:20

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 Aufrufe • vor 2 Monaten

Introducing Voyager: the open harness for S-tier video, graphics and games. The Codex for creative work. Most AI tools are built for coding. Voyager is designed to get the best creative results from models like Opus, Astra and DeepSeek. It comes with free graphics, music and video editing tools - or, it can drive Blender, Resolve, After Effects, Ableton and 100+ others. Everything in this thread was made with Voyager. A few of our favorites:
1:24

Introducing Voyager: the open harness for S-tier video, graphics and games. The Codex for creative work. Most AI tools are built for coding. Voyager is designed to get the best creative results from models like Opus, Astra and DeepSeek. It comes with free graphics, music and video editing tools - or, it can drive Blender, Resolve, After Effects, Ableton and 100+ others. Everything in this thread was made with Voyager. A few of our favorites:

Anvisha

2,493,732 Aufrufe • vor 5 Tagen

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace
1:37

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

OpenBMB

13,996 Aufrufe • vor 9 Monaten

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:
0:23

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:

TITLES

2,748,627 Aufrufe • vor 6 Monaten

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: 📝 Blog: 🔗 GitHub: ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful Shang Zhu and advised by James Zou ! All features powered by Together AI . Try it and let us know what you think! 🎻
0:41

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: 📝 Blog: 🔗 GitHub: ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful Shang Zhu and advised by James Zou ! All features powered by Together AI . Try it and let us know what you think! 🎻

Kevin Lin

139,822 Aufrufe • vor 5 Monaten

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.
0:26

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 Aufrufe • vor 2 Monaten

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.
1:18

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Kanika

17,726 Aufrufe • vor 4 Monaten

🚀 Introducing NemoVideo Skill — The World's First Pro Video Editing Skill for AI Agents If every lobster has a dream, Nemo’s was to stop mopping and start directing. 🦞🎬 Today, that dream ships. NemoVideo Skill, is the world’s first all-in-one professional video editing skill for your OpenClaw agent. What NemoVideo Skill can do for you: 🎬 Research, script, and storyboard — from a single prompt 🎙️ Generate AI voices, auto-mix audio, and source footage ✅ Self-audit and deliver a full timeline — ready to export Huge thanks and respect to OpenClaw🦞 and Peter Steinberger 🦞 for building the infrastructure that makes this possible. ⭐Want to try it? Just tell your OpenClaw: “Install the nemo-video skill from ClawHub.” That’s it. Your lobster will handle the rest. 🦞 ❤️Love what Nemo’s building? Star & rate on GitHub/ClawHub → → Screenshot your star & DM us — we’ll send you free credits! 🎬 Start creating → #NemoVideo #AgenticAI #AIvideo
0:36

🚀 Introducing NemoVideo Skill — The World's First Pro Video Editing Skill for AI Agents If every lobster has a dream, Nemo’s was to stop mopping and start directing. 🦞🎬 Today, that dream ships. NemoVideo Skill, is the world’s first all-in-one professional video editing skill for your OpenClaw agent. What NemoVideo Skill can do for you: 🎬 Research, script, and storyboard — from a single prompt 🎙️ Generate AI voices, auto-mix audio, and source footage ✅ Self-audit and deliver a full timeline — ready to export Huge thanks and respect to OpenClaw🦞 and Peter Steinberger 🦞 for building the infrastructure that makes this possible. ⭐Want to try it? Just tell your OpenClaw: “Install the nemo-video skill from ClawHub.” That’s it. Your lobster will handle the rest. 🦞 ❤️Love what Nemo’s building? Star & rate on GitHub/ClawHub → → Screenshot your star & DM us — we’ll send you free credits! 🎬 Start creating → #NemoVideo #AgenticAI #AIvideo

NemoVideo

108,380 Aufrufe • vor 7 Monaten

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.
0:47

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.

Aakash Gupta

10,774 Aufrufe • vor 1 Monat

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️
1:36

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

AI at Meta

150,477 Aufrufe • vor 2 Jahren

Video Model Comparison: Text to Video → Veo 3.1 → Sora 2 Pro → Kling 2.6 → Luma Ray3 → Wan 2.5 → Hailuo 2.3 → LTX-2 Pro → Seedance Pro Many of the new models automatically generate sound with video results including Veo 3.1, Sora 2 Pro, Kling 2.6, Wan 2.5, and LTX-2 Pro. I used Mirelo AI SFX and ElevenLabs to add sound to the others. I used the same prompt on each model 4x and chose the best result: Meteor Shower Panic Subject: [Father holding daughter's hand, looking up] Action: [Running through a suburban street, looking up as meteors streak across the sky, a small impact occurs nearby blowing wind and dust at them] Scene: [Suburban street, night, streetlights, burning trails in sky] Style: [Cinematic disaster, low angle tracking shot, high contrast, lens flares from meteors] Audio: Audio: sonic booms, wind rushing, car alarms triggered, shouting. Technical: [daytime, calm, sunny, happy] Which one is your favorite?
1:33

Video Model Comparison: Text to Video → Veo 3.1 → Sora 2 Pro → Kling 2.6 → Luma Ray3 → Wan 2.5 → Hailuo 2.3 → LTX-2 Pro → Seedance Pro Many of the new models automatically generate sound with video results including Veo 3.1, Sora 2 Pro, Kling 2.6, Wan 2.5, and LTX-2 Pro. I used Mirelo AI SFX and ElevenLabs to add sound to the others. I used the same prompt on each model 4x and chose the best result: Meteor Shower Panic Subject: [Father holding daughter's hand, looking up] Action: [Running through a suburban street, looking up as meteors streak across the sky, a small impact occurs nearby blowing wind and dust at them] Scene: [Suburban street, night, streetlights, burning trails in sky] Style: [Cinematic disaster, low angle tracking shot, high contrast, lens flares from meteors] Audio: Audio: sonic booms, wind rushing, car alarms triggered, shouting. Technical: [daytime, calm, sunny, happy] Which one is your favorite?

Heather Cooper

20,422 Aufrufe • vor 10 Monaten

OiiOii AI is like Nano Banana but for Videos !! 🚨 Most AI video tools limit you to pre-made templates But I just turned a social media trend into a reusable AI workflow !! I created this in just 10 minutes using OiiOii AI's new Skill Maker feature to replace "Ronaldo" with "Sundar Pichai" I uploaded the reference video.... And OiiOii extracted the EXACT style, pacing & structure OiiOii AI is the ultimate shortcut to catch up with viral trends while keeping your content 100% original and unique. Its also 100% copyright-safe content 🙌 Try now with "FREE" AI Credits👇 Join the Discord: #AIAnimation #OiiOii
0:31

OiiOii AI is like Nano Banana but for Videos !! 🚨 Most AI video tools limit you to pre-made templates But I just turned a social media trend into a reusable AI workflow !! I created this in just 10 minutes using OiiOii AI's new Skill Maker feature to replace "Ronaldo" with "Sundar Pichai" I uploaded the reference video.... And OiiOii extracted the EXACT style, pacing & structure OiiOii AI is the ultimate shortcut to catch up with viral trends while keeping your content 100% original and unique. Its also 100% copyright-safe content 🙌 Try now with "FREE" AI Credits👇 Join the Discord: #AIAnimation #OiiOii

COLAW

131,265 Aufrufe • vor 2 Monaten

ComfyUI is now the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weights have been downloaded through Comfy close to 20 million times. Not one of those downloads paid the lab a cent. That is the open-weight problem. Training frontier models is expensive. Adoption is not revenue. If open models are going to keep pace with the biggest closed labs, the labs need a way to get paid. So we built the bridge. Enterprises, studios, and agencies license through us. The labs get incentive to keep researching. Independent creators keep building exactly as they do now, funded by the organizations with budgets. A license only gets you the model. Our Forward Deployed Creatives embed with your team, train LoRAs on your style, build production workflows in your environment, and leave your people able to run and extend all of it. What they build is yours to keep. MiniMax is where we start, not where we stop. My assertion is that open-weight labs that survive the next two years will not be the ones with the best benchmarks. They will be the ones that solve distribution to paying customers first. Try for Free | Request a License today ⬇️
2:35

ComfyUI is now the first and only commercial license distributor for MiniMax (official)'s generative media models. MiniMax open weights have been downloaded through Comfy close to 20 million times. Not one of those downloads paid the lab a cent. That is the open-weight problem. Training frontier models is expensive. Adoption is not revenue. If open models are going to keep pace with the biggest closed labs, the labs need a way to get paid. So we built the bridge. Enterprises, studios, and agencies license through us. The labs get incentive to keep researching. Independent creators keep building exactly as they do now, funded by the organizations with budgets. A license only gets you the model. Our Forward Deployed Creatives embed with your team, train LoRAs on your style, build production workflows in your environment, and leave your people able to run and extend all of it. What they build is yours to keep. MiniMax is where we start, not where we stop. My assertion is that open-weight labs that survive the next two years will not be the ones with the best benchmarks. They will be the ones that solve distribution to paying customers first. Try for Free | Request a License today ⬇️

Yoland Yan

14,985 Aufrufe • vor 1 Monat

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions! 🎥 Highlights: ✅Subject Consistency: Maintains identity across single & multi-subject video generation. ✅Multimodal Inputs: Supports text, images, audio, and video for highly controlled outputs. ✅High-Quality Output: Industry-leading detail, motion smoothness, and lighting realism. Key Features: 1️⃣Single-Subject Video: Upload an image + text (e.g., “He’s walking a dog”) to create coherent videos with new actions, outfits, and scenes. 2️⃣Multi-Subject Video: Generate videos with multiple subjects (e.g., a man drinking coffee in a cozy room) from separate image inputs. 3️⃣Audio-Driven Video: Sync audio with visuals for talking or singing in any scene—perfect for digital avatars, virtual customer service, and more. 4️⃣Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements. Dive Deeper: 🌐Project: 📝Technical Details: 💻Code: The single-subject video capability is open-sourced and live on the Hunyuan website, with more features to be released soon! 👉 Try it now: #HunyuanCustom #VideoGeneration #AI #TencentHunyuan
0:40

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions! 🎥 Highlights: ✅Subject Consistency: Maintains identity across single & multi-subject video generation. ✅Multimodal Inputs: Supports text, images, audio, and video for highly controlled outputs. ✅High-Quality Output: Industry-leading detail, motion smoothness, and lighting realism. Key Features: 1️⃣Single-Subject Video: Upload an image + text (e.g., “He’s walking a dog”) to create coherent videos with new actions, outfits, and scenes. 2️⃣Multi-Subject Video: Generate videos with multiple subjects (e.g., a man drinking coffee in a cozy room) from separate image inputs. 3️⃣Audio-Driven Video: Sync audio with visuals for talking or singing in any scene—perfect for digital avatars, virtual customer service, and more. 4️⃣Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements. Dive Deeper: 🌐Project: 📝Technical Details: 💻Code: The single-subject video capability is open-sourced and live on the Hunyuan website, with more features to be released soon! 👉 Try it now: #HunyuanCustom #VideoGeneration #AI #TencentHunyuan

Tencent HY

191,908 Aufrufe • vor 1 Jahr

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.
1:18

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

nikshep

41,503 Aufrufe • vor 7 Monaten

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!
0:26

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,982 Aufrufe • vor 6 Monaten

America has the edge in the world’s most powerful AI models, no question. But China is playing a different game: efficiency, scale, and global deployment. Kyle Chan from Brookings China explains: "Does winning mean developing the world's most powerful AI models? If yes, then the us has the decisive lead. American ai models are widely recognized as the best in the world on virtually every metric you can think of, from math and reasoning to coding and AI agents, American private companies continue to set the pace at the technological frontier supported by deep capital markets, a dynamic innovation ecosystem, and the best talent from around the world. China's AI models are improving quickly but continue to lag behind. Chinese AI companies face real constraints on compute due to our export controls and their own limited capital resources, so instead they're prioritizing other goals. They're focused on efficiency, building models that are cheaper to train and run. They're focused on adoption using an open source strategy to win users around the world, and they're focused on integration with other platforms and services. On sheer performance, I would expect the gap between our models and theirs to persist or even widen over time. But model performance is not everything."
1:10

America has the edge in the world’s most powerful AI models, no question. But China is playing a different game: efficiency, scale, and global deployment. Kyle Chan from Brookings China explains: "Does winning mean developing the world's most powerful AI models? If yes, then the us has the decisive lead. American ai models are widely recognized as the best in the world on virtually every metric you can think of, from math and reasoning to coding and AI agents, American private companies continue to set the pace at the technological frontier supported by deep capital markets, a dynamic innovation ecosystem, and the best talent from around the world. China's AI models are improving quickly but continue to lag behind. Chinese AI companies face real constraints on compute due to our export controls and their own limited capital resources, so instead they're prioritizing other goals. They're focused on efficiency, building models that are cheaper to train and run. They're focused on adoption using an open source strategy to win users around the world, and they're focused on integration with other platforms and services. On sheer performance, I would expect the gap between our models and theirs to persist or even widen over time. But model performance is not everything."

Select Committee on China

60,135 Aufrufe • vor 6 Monaten

AI has transformed how video is created. We think the next wave is about understanding it. Over the past few years, we've seen remarkable advances in video generation, editing, avatars, and creative tooling. An increasingly important problem is teaching machines to search, analyze, reason over, and extract insight from video - across massive libraries and live streams alike. We're calling this video intelligence, and we're actively looking to back founders building here. We're most excited about companies pushing on the core capabilities: - Video-native models - multimodal embeddings, temporal reasoning, and retrieval built specifically for video rather than adapted from image or text - Real-time and large-scale pipelines - infrastructure for processing, indexing, and querying video at the speed and scale enterprises actually need - Agentic and reasoning layers - systems that don't just retrieve clips but answer questions, surface anomalies, and take action on what they see The models and infrastructure to make this real are appearing to be crossing a capability threshold right now. Multimodal foundation models are maturing, storage costs have collapsed, and enterprises are sitting on years of unstructured video with no way to use it. That infrastructure unlocks a wide range of applications including media and sports workflows, security and physical operations, enterprise knowledge management, advertising analytics, robotics, and consumer products, where video has historically been dark data. If you're building in video intelligence at the model layer, the platform layer, or in a vertical application, we'd love to talk!
1:41

AI has transformed how video is created. We think the next wave is about understanding it. Over the past few years, we've seen remarkable advances in video generation, editing, avatars, and creative tooling. An increasingly important problem is teaching machines to search, analyze, reason over, and extract insight from video - across massive libraries and live streams alike. We're calling this video intelligence, and we're actively looking to back founders building here. We're most excited about companies pushing on the core capabilities: - Video-native models - multimodal embeddings, temporal reasoning, and retrieval built specifically for video rather than adapted from image or text - Real-time and large-scale pipelines - infrastructure for processing, indexing, and querying video at the speed and scale enterprises actually need - Agentic and reasoning layers - systems that don't just retrieve clips but answer questions, surface anomalies, and take action on what they see The models and infrastructure to make this real are appearing to be crossing a capability threshold right now. Multimodal foundation models are maturing, storage costs have collapsed, and enterprises are sitting on years of unstructured video with no way to use it. That infrastructure unlocks a wide range of applications including media and sports workflows, security and physical operations, enterprise knowledge management, advertising analytics, robotics, and consumer products, where video has historically been dark data. If you're building in video intelligence at the model layer, the platform layer, or in a vertical application, we'd love to talk!

Jason Cui

36,829 Aufrufe • vor 5 Monaten

STOP PAYING $200/MO FOR AI: 900 FREE MODELS FROM GPT, CLAUDE, KIMI AND DEEPSEEK IN ONE DIRECTORY freeLLM tracks every free tier, signup credit and daily quota across 58 providers so you never pay for what's already free > 900 models, updated daily as new promos land > filters for free forever, no card, no signup, open source > text, code, image, audio, video, embeddings > live status on every model, dead ones filtered out frontier models like GPT-6 Astra, Claude Fable 5.1, DeepSeek V4, MiniMax M3 and Kimi K3 show up through provider credits and quotas everything else runs on tiers that never expire 20K people found it in the first month that's $2,400 a year back in your pocket for one bookmark tab
0:20

STOP PAYING $200/MO FOR AI: 900 FREE MODELS FROM GPT, CLAUDE, KIMI AND DEEPSEEK IN ONE DIRECTORY freeLLM tracks every free tier, signup credit and daily quota across 58 providers so you never pay for what's already free > 900 models, updated daily as new promos land > filters for free forever, no card, no signup, open source > text, code, image, audio, video, embeddings > live status on every model, dead ones filtered out frontier models like GPT-6 Astra, Claude Fable 5.1, DeepSeek V4, MiniMax M3 and Kimi K3 show up through provider credits and quotas everything else runs on tiers that never expire 20K people found it in the first month that's $2,400 a year back in your pocket for one bookmark tab

Mr. Buzzoni

11,519 Aufrufe • vor 1 Monat