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。

Most reframe tools crop, downsize, or hallucinate. Introducing the LTX Reframe API. Expand any video to a new aspect ratio. The original frame stays untouched. The model generates only what’s beyond the edges. • Full source length, up to 60s • Native 1080p • 16:9, 9:16, 1:1, 4:5 •... show more

LTX.io

38,080 subscribers

685,405 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

Introducing LTX-2.3 Our most production-ready model yet. The fastest 4K video generation in the world with built-in native dialogue. Here’s what’s new 🧵 1/9

LTX Studio

678,210 次观看 • 6 个月前

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

A look at the video outpainting workflow in ComfyUI using LTX 2.3. 🎥 Instead of cropping your 16:9 footage for vertical, use this IC-LoRA setup to generate the missing space and keep your original frame. Shout out to Mohamed Oumoumad for their open source contribution. Link to workflow below! 👇

ComfyUI

19,041 次观看 • 4 个月前

Quick FOV talk on why you shouldn't use 90 FOV on 16:9 and why 74 FOV on 16:9 is a viable thing to do. FOV isn't just 1 slider, it's affected by the aspect ratio. Especially important for Console Players that cannot change their aspect ratio.

Quick FOV talk on why you shouldn't use 90 FOV on 16:9 and why 74 FOV on 16:9 is a viable thing to do. FOV isn't just 1 slider, it's affected by the aspect ratio. Especially important for Console Players that cannot change their aspect ratio.

Noob

45,328 次观看 • 1 年前

ADOBE EDITORS JUST GOT THEIR BIGGEST UPGRADE IN YEARS. and this time, it came from outside. Higgsfield is now inside Premiere Pro and After Effects as a native plugin. 5 tools, zero exports: → reframe to any ratio — subject stays centered → remove BG without green screen → upscale to 4K or 8K → draw on the frame to edit it → generate clips from a prompt, direct to timeline the workflow that used to eat your entire afternoon? it's now one panel inside Adobe. if you edit video, you need to try this. look at this result ⬇️

ADOBE EDITORS JUST GOT THEIR BIGGEST UPGRADE IN YEARS. and this time, it came from outside. Higgsfield is now inside Premiere Pro and After Effects as a native plugin. 5 tools, zero exports: → reframe to any ratio — subject stays centered → remove BG without green screen → upscale to 4K or 8K → draw on the frame to edit it → generate clips from a prompt, direct to timeline the workflow that used to eat your entire afternoon? it's now one panel inside Adobe. if you edit video, you need to try this. look at this result ⬇️

marcus

85,027 次观看 • 3 个月前

Introducing LTX-2: the most complete open-source AI creative engine. - Synchronized audio and video generation - Native 4K fidelity, up to 50 fps and 10 s+ sequences - API-first design for seamless integration into creative pipelines - Runs efficiently on consumer GPUs - Fully open and accessible, with weights releasing later this year

Introducing LTX-2: the most complete open-source AI creative engine. - Synchronized audio and video generation - Native 4K fidelity, up to 50 fps and 10 s+ sequences - API-first design for seamless integration into creative pipelines - Runs efficiently on consumer GPUs - Fully open and accessible, with weights releasing later this year

LTX

1,700,938 次观看 • 10 个月前

Introducing LTX-2.5, the world model the world builds on. One of the biggest upgrades yet to the model already powering film, robotics, and real-time workflows. Higher pixel fidelity, multishot scenes that hold together across cuts, and a pretrained foundation built to be finetuned across domains. Plus: Diffusion Fidelity Rendering, a new rendering approach built for pixel quality that holds up frame by frame, even on a cinema screen. This isn't a tool you rent. It's a foundation you build on, open and yours.

Introducing LTX-2.5, the world model the world builds on. One of the biggest upgrades yet to the model already powering film, robotics, and real-time workflows. Higher pixel fidelity, multishot scenes that hold together across cuts, and a pretrained foundation built to be finetuned across domains. Plus: Diffusion Fidelity Rendering, a new rendering approach built for pixel quality that holds up frame by frame, even on a cinema screen. This isn't a tool you rent. It's a foundation you build on, open and yours.

LTX.io

13,723,304 次观看 • 21 天前

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

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 次观看 • 1 个月前

This is something I talked about in my review of Pixar's Elio. Another reviewer, JesterBell, pointed out that nearly every shot has the action framed in the center, and speculated this was to make it easy for influencers to crop for TikTok and YouTube Shorts. I even cropped the trailer to 9:16 just to see, and yes, like 80% of the shots fit a vertical frame without having to move anything around. The movie itself has an aspect ratio of 2.4 (12:5), so squeezing the action into the middle like this means they're only really using a quarter of the frame.

This is something I talked about in my review of Pixar's Elio. Another reviewer, JesterBell, pointed out that nearly every shot has the action framed in the center, and speculated this was to make it easy for influencers to crop for TikTok and YouTube Shorts. I even cropped the trailer to 9:16 just to see, and yes, like 80% of the shots fit a vertical frame without having to move anything around. The movie itself has an aspect ratio of 2.4 (12:5), so squeezing the action into the middle like this means they're only really using a quarter of the frame.

Possum Reviews

37,506 次观看 • 7 个月前

Turn one product photo into a finished video ad. Storyboard to video with sound in minutes - inside a chat. Drop in a product photo and one sentence. Minutes later: a 9-frame storyboard, then a finished video ad with sound, ready to run. Powered by GPT Image 2 → Seedance 2.0 - one of the strongest storyboard-to-video pairings available right now, both in one chat at Why it's different: → No subscription. Most Seedance providers lock you into a monthly plan whether you make one clip or a hundred. Sogni charges per generation on a people-powered consumer GPU network. → Agent-native. Run the whole pipeline from Claude, Codex, or Hermes - "turn this into a 9-shot storyboard video" straight from your terminal. → Right model for the job. Frontier models when you need them, open-source models like LTX 2.3 when you don't. One photo. One sentence. One finished ad. Your move ↓

Turn one product photo into a finished video ad. Storyboard to video with sound in minutes - inside a chat. Drop in a product photo and one sentence. Minutes later: a 9-frame storyboard, then a finished video ad with sound, ready to run. Powered by GPT Image 2 → Seedance 2.0 - one of the strongest storyboard-to-video pairings available right now, both in one chat at Why it's different: → No subscription. Most Seedance providers lock you into a monthly plan whether you make one clip or a hundred. Sogni charges per generation on a people-powered consumer GPU network. → Agent-native. Run the whole pipeline from Claude, Codex, or Hermes - "turn this into a 9-shot storyboard video" straight from your terminal. → Right model for the job. Frontier models when you need them, open-source models like LTX 2.3 when you don't. One photo. One sentence. One finished ad. Your move ↓

Sogni.ai

1,089,620 次观看 • 2 个月前

‼️ CANDACE CAUGHT LYING AND NOW DOUBLING DOWN Candace is using tricky wording like always. There wasn't an aspect ratio adjustment. The security camera used on the UVU Campus here is a wide angle lens. Then it is shown on TV only. Below, you will see what that SAME FOOTAGE looks like with no edits - just the crop changed to a 16:9 ratio. It very much looks like Tyler Robinson and no one had to zoom in like you did to hide everything on the outside parts of the video!

‼️ CANDACE CAUGHT LYING AND NOW DOUBLING DOWN Candace is using tricky wording like always. There wasn't an aspect ratio adjustment. The security camera used on the UVU Campus here is a wide angle lens. Then it is shown on TV only. Below, you will see what that SAME FOOTAGE looks like with no edits - just the crop changed to a 16:9 ratio. It very much looks like Tyler Robinson and no one had to zoom in like you did to hide everything on the outside parts of the video!

Nick Matau

67,363 次观看 • 11 天前

Yes, 2024 is shaping up a big year for robotics! Introducing Covariant's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world. But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1 tokenizes 5 modalities: video, keyframes, text, sensory readings, robot actions. Any-to-any means RFM-1 can handle any subset on the input and any subset on the output.

Yes, 2024 is shaping up a big year for robotics! Introducing Covariant's RFM-1, which just like Sora can generate video, but RFM-1 does it for robotic interaction with the world. But there is so much more it can do. RFM-1 is a multimodal any-to-any sequence model. RFM-1 tokenizes 5 modalities: video, keyframes, text, sensory readings, robot actions. Any-to-any means RFM-1 can handle any subset on the input and any subset on the output.

Pieter Abbeel

167,056 次观看 • 2 年前

🆕 Need for Speed: Underground 2 — Widescreen Fix completely overhauled! The game that introduced open-world racing to Need for Speed — now completely modernized for an unforgettable experience. 🔗 Download: • 🔧 Fixes: • Any resolution, any aspect ratio — ultrawide included • Corrected aspect ratio across all rendered elements • HUD repositioned & scaled with optional 16:9, 21:9, or custom constraints • Accurate hor+ FOV • FMVs fullscreen with crop/stretch for 16:9, auto-fit for narrower ratios • Cutscene letterboxing removed ✨ New options: • Skip intro FMVs • Borderless, bordered, resizable, or borderless fullscreen windowed mode • FPS limit — uncapped, fixed, or monitor-synced (including 2×) • High FPS cutscenes — raises the cutscene cap • Xbox, PlayStation, or PC text gamepad labels with fixed front-end bindings • Configurable analog deadzones for both sticks • Custom save directory & optional registry-free settings • Single core affinity fix — prevents crashes on modern multi-core CPUs • Xbox 360 gamma curve and more... 🎥 Full free-look camera — mouse & right stick, configurable sensitivity, timeout, return speed, and axis inversion.

🆕 Need for Speed: Underground 2 — Widescreen Fix completely overhauled! The game that introduced open-world racing to Need for Speed — now completely modernized for an unforgettable experience. 🔗 Download: • 🔧 Fixes: • Any resolution, any aspect ratio — ultrawide included • Corrected aspect ratio across all rendered elements • HUD repositioned & scaled with optional 16:9, 21:9, or custom constraints • Accurate hor+ FOV • FMVs fullscreen with crop/stretch for 16:9, auto-fit for narrower ratios • Cutscene letterboxing removed ✨ New options: • Skip intro FMVs • Borderless, bordered, resizable, or borderless fullscreen windowed mode • FPS limit — uncapped, fixed, or monitor-synced (including 2×) • High FPS cutscenes — raises the cutscene cap • Xbox, PlayStation, or PC text gamepad labels with fixed front-end bindings • Configurable analog deadzones for both sticks • Custom save directory & optional registry-free settings • Single core affinity fix — prevents crashes on modern multi-core CPUs • Xbox 360 gamma curve and more... 🎥 Full free-look camera — mouse & right stick, configurable sensitivity, timeout, return speed, and axis inversion.

Fusion Fix

19,211 次观看 • 4 个月前

🆕 Need for Speed: Most Wanted — Widescreen Fix updated! The most iconic NFS of its generation — now with the visual and quality-of-life treatment it deserves. 🔗 Download: • 🔧 Fixes: • Native support for any resolution, including ultrawide • Corrected aspect ratio for all rendered elements • HUD repositioned & scaled with optional 16:9, 21:9, or custom constraints, configurable UI scale & auto-fit mode • Xbox 360 or mathematically correct hor+ FOV scaling • FMVs fullscreen with crop/stretch, auto-fit for narrower ratios ✨ New options: • Skip intro FMVs • Borderless, bordered, resizable, or borderless fullscreen windowed mode • Configurable simulation refresh rate — sync to monitor or double it • Xbox, PlayStation, or text-only gamepad labels with fixed bindings • Configurable analog deadzones • Shadow resolution up to 16384 — improved LOD, and auto-scaling by aspect ratio • Shadow map format selection: D24S8, INTZ, DF16, DF24, or forced sharp shadows • Custom save directory & registry-free settings • High spec audio (forced 44100 Hz), Xbox 360 gamma and more... 🎥 Free-look camera — mouse & right stick with full configurability.

🆕 Need for Speed: Most Wanted — Widescreen Fix updated! The most iconic NFS of its generation — now with the visual and quality-of-life treatment it deserves. 🔗 Download: • 🔧 Fixes: • Native support for any resolution, including ultrawide • Corrected aspect ratio for all rendered elements • HUD repositioned & scaled with optional 16:9, 21:9, or custom constraints, configurable UI scale & auto-fit mode • Xbox 360 or mathematically correct hor+ FOV scaling • FMVs fullscreen with crop/stretch, auto-fit for narrower ratios ✨ New options: • Skip intro FMVs • Borderless, bordered, resizable, or borderless fullscreen windowed mode • Configurable simulation refresh rate — sync to monitor or double it • Xbox, PlayStation, or text-only gamepad labels with fixed bindings • Configurable analog deadzones • Shadow resolution up to 16384 — improved LOD, and auto-scaling by aspect ratio • Shadow map format selection: D24S8, INTZ, DF16, DF24, or forced sharp shadows • Custom save directory & registry-free settings • High spec audio (forced 44100 Hz), Xbox 360 gamma and more... 🎥 Free-look camera — mouse & right stick with full configurability.

Fusion Fix

35,547 次观看 • 4 个月前

🆕 Need for Speed: Underground - Widescreen Fix rebuilt from the ground up! The game that defined an era of street racing now runs even better on modern displays. 🔗 Download: • 🔧 Fixes: • Native support for any resolution, including ultrawide • Corrected aspect ratio for all rendered elements • HUD repositioned & scaled to match your display - with optional 16:9, 21:9, or custom constraints • Hor+ field of view • FMVs display fullscreen in 16:9 with crop or stretch mode • Fixed the black background on magazine cover screens ✨ New options: • Skip intro FMVs • Borderless, bordered or borderless fullscreen windowed mode • FPS limit - uncapped, fixed, or synced to your monitor refresh rate (including 2×) • Xbox & PlayStation gamepad icons with fixed front-end bindings • Configurable analog stick deadzones • Custom save directory, Xbox 360 gamma and more 🎥 Free-look camera with mouse & right stick support - adjustable sensitivity, reset timeout, return speed, and axis inversion. Experience Underground like never before.

🆕 Need for Speed: Underground - Widescreen Fix rebuilt from the ground up! The game that defined an era of street racing now runs even better on modern displays. 🔗 Download: • 🔧 Fixes: • Native support for any resolution, including ultrawide • Corrected aspect ratio for all rendered elements • HUD repositioned & scaled to match your display - with optional 16:9, 21:9, or custom constraints • Hor+ field of view • FMVs display fullscreen in 16:9 with crop or stretch mode • Fixed the black background on magazine cover screens ✨ New options: • Skip intro FMVs • Borderless, bordered or borderless fullscreen windowed mode • FPS limit - uncapped, fixed, or synced to your monitor refresh rate (including 2×) • Xbox & PlayStation gamepad icons with fixed front-end bindings • Configurable analog stick deadzones • Custom save directory, Xbox 360 gamma and more 🎥 Free-look camera with mouse & right stick support - adjustable sensitivity, reset timeout, return speed, and axis inversion. Experience Underground like never before.

Fusion Fix

50,893 次观看 • 4 个月前

The simplest AI business I've seen: Recommend AI tools to small business owners. Charge $999. The entire model in 5 steps: 1) Record a 45-min call with the owner 2) Drop the transcript into Claude 3) Claude finds the exact tools for their pain points 4) Send them the list of 3-7 tools 5) Charge $999 The guarantee: save them 5 hours a week or full refund. Average client gets 7 hours back. Every week. This is perfect for the person who's already the "AI friend" in every group chat.

The simplest AI business I've seen: Recommend AI tools to small business owners. Charge $999. The entire model in 5 steps: 1) Record a 45-min call with the owner 2) Drop the transcript into Claude 3) Claude finds the exact tools for their pain points 4) Send them the list of 3-7 tools 5) Charge $999 The guarantee: save them 5 hours a week or full refund. Average client gets 7 hours back. Every week. This is perfect for the person who's already the "AI friend" in every group chat.

The Startup Ideas Podcast (SIP) 🧃

22,739 次观看 • 1 个月前

Goodnight, 𝕏..·˚ ༘ ☾ ⋆｡˚ ☄︎ Newscast about xAI, SpaceX, Starlink, Neuralink, 𝕏, and Grok. Created using the xAI Video API. I upscaled the final frame to use as the starting point for the next clip's generation, but it only helped marginally. However, I found a paper called "FreeInit: Bridging Initialization Gap in Video Diffusion Models" that I'm going to try tomorrow to fix the drifting problem. The approach: 1. FFT both images (anchor frame + last frame) 2. Low-pass filter on anchor (structure/color/layout) 3. High-pass filter on last frame (details/edges/motion) 4. Combine and IFFT back

Goodnight, 𝕏..·˚ ༘ ☾ ⋆｡˚ ☄︎ Newscast about xAI, SpaceX, Starlink, Neuralink, 𝕏, and Grok. Created using the xAI Video API. I upscaled the final frame to use as the starting point for the next clip's generation, but it only helped marginally. However, I found a paper called "FreeInit: Bridging Initialization Gap in Video Diffusion Models" that I'm going to try tomorrow to fix the drifting problem. The approach: 1. FFT both images (anchor frame + last frame) 2. Low-pass filter on anchor (structure/color/layout) 3. High-pass filter on last frame (details/edges/motion) 4. Combine and IFFT back

tetsuo

97,901 次观看 • 7 个月前

300 agents can find 1,000 sources. that still doesn’t make the research good the interesting part starts when those sources are forced to check each other. in K3 graph-native setup: 300 agents → 140 linked sources → 100% traceable claims → 9 contradictions surfaced one source confirms a number. another challenges it. a third connects the same entity from a different angle. so instead of: source → summary you get: source → entity → overlap → contradiction → verification → graph every new source becomes a node. if 3–4 independent sources support the same claim, confidence goes up. if 2 sources disagree, the contradiction gets flagged. if a claim has only 1 supporting source, it stays weak. a normal research workflow could have quietly shipped those 9 contradictions as facts. that’s why the breakthrough isn’t just 300 agents running in parallel. full breakdown in the article below.

300 agents can find 1,000 sources. that still doesn’t make the research good the interesting part starts when those sources are forced to check each other. in K3 graph-native setup: 300 agents → 140 linked sources → 100% traceable claims → 9 contradictions surfaced one source confirms a number. another challenges it. a third connects the same entity from a different angle. so instead of: source → summary you get: source → entity → overlap → contradiction → verification → graph every new source becomes a node. if 3–4 independent sources support the same claim, confidence goes up. if 2 sources disagree, the contradiction gets flagged. if a claim has only 1 supporting source, it stays weak. a normal research workflow could have quietly shipped those 9 contradictions as facts. that’s why the breakthrough isn’t just 300 agents running in parallel. full breakdown in the article below.

Ricker

227,257 次观看 • 13 天前

OpenAI gpt-oss 120B orchestrates a full video using Hugging Face spaces! 🤯 All of it, in one SINGLE prompt: create an image of a Labrador and use it to generate a simple video of it 🛠️ Tools used: 1. Flux.1 Krea Dev by Black Forest Labs 2. LTX Fast by Lightricks That's it, gpt-oss 120B is one of the BEST open source models I've used for tool calling so far! Kudos OpenAI 🤗

OpenAI gpt-oss 120B orchestrates a full video using Hugging Face spaces! 🤯 All of it, in one SINGLE prompt: create an image of a Labrador and use it to generate a simple video of it 🛠️ Tools used: 1. Flux.1 Krea Dev by Black Forest Labs 2. LTX Fast by Lightricks That's it, gpt-oss 120B is one of the BEST open source models I've used for tool calling so far! Kudos OpenAI 🤗

Vaibhav (VB) Srivastav

45,098 次观看 • 1 年前

Most blockchains weren’t built for real world finance. We sat down with Daniel Marin, CEO of Nexus, to break down why how Nexus has built a purposeful Layer 1 for verifiable finance. We cover the Nexus Exchange, $USDX as the native dollar, predictable execution powered by zkProofs, and how stablecoin yield can create sustainable onchain revenue models. Timestamps: 0:00 – The Problem: Why Ethereum Isn’t Built for Traditional Finance 0:53 – Introducing Nexus: A Purpose-Built Layer 1 for Verifiable Finance 4:44 – How Zero Knowledge Scaling Enables Low Latency Trading 6:24 – Tokenization on Ethereum vs High Frequency Verifiable Finance 8:30 – Nexus Timeline: From Stanford to 3M+ Users 12:34 – USDX Explained: A Native Stablecoin Backed by T-Bills 16:16 – How Nexus Captures Stablecoin Yield & Creates a Value Flywheel 26:15 – What’s Coming Next: Token Campaigns & Mainnet Roadmap

Most blockchains weren’t built for real world finance. We sat down with Daniel Marin, CEO of Nexus, to break down why how Nexus has built a purposeful Layer 1 for verifiable finance. We cover the Nexus Exchange, $USDX as the native dollar, predictable execution powered by zkProofs, and how stablecoin yield can create sustainable onchain revenue models. Timestamps: 0:00 – The Problem: Why Ethereum Isn’t Built for Traditional Finance 0:53 – Introducing Nexus: A Purpose-Built Layer 1 for Verifiable Finance 4:44 – How Zero Knowledge Scaling Enables Low Latency Trading 6:24 – Tokenization on Ethereum vs High Frequency Verifiable Finance 8:30 – Nexus Timeline: From Stanford to 3M+ Users 12:34 – USDX Explained: A Native Stablecoin Backed by T-Bills 16:16 – How Nexus Captures Stablecoin Yield & Creates a Value Flywheel 26:15 – What’s Coming Next: Token Campaigns & Mainnet Roadmap

Crypto Coin Show

10,669 次观看 • 6 个月前