Tom Factor

Senior Creative Director @ltx_io

[Tom Factor @tom_factor]

A historic win deserves a special cover. Audio and video, all @ltx_io. 🇦🇷

[CG Channel @theCGchannel]

Read our round-up of last week's updates to key CG tools, like:

• New #VFX features in video AI model #LTX
• A dedicated particle effects toolset in #motiongraphics app #Caddis
• Updates to #RailClone for #3dsMax and #RTXRender for #iClone

https://t.co/ARI84d0Wk8

#VFX

[Mohamed Oumoumad @MedOumoumad]

I trained a bunch of image models for SDR-to-HDR, only to realize @ltx_io 2.5 does it perfectly and fast!
With tiled fusion it runs at any resolution, and the same goes for upscaling/refining.
Never imagined a video/world model would be my go-to for image upscaling and HDR.

[AmirMušić @AmirMushich]

Rebuilt this demo for a real brand with Astra 6 + LTX-2.5 (video model)

→ I took real product photos
→ generated rotation for each one with LTX API
→ coded the UI with Astra-6 in Codex

Original concept by @cambreedesigns

[Winbush @JonathanWinbush]

LTX's new Alpha Gen (beta) generates clean alpha mattes right inside ComfyUI, hair, smoke, soft edges, no green screen needed. Full tutorial: https://t.co/MiZrUmEtkw

@ltx_io
@ComfyUI
#comfyui #ltx25 #alphagen #vfx

[Tom Factor @tom_factor]

@heydoughogan 👑

[田中義弘 | taziku CEO / AI × Creative @taziku_co]

VFX制作で時間のかかる工程が、また一つAI化。

LTXがAlpha Gen（Beta）を公開。
普通のRGB動画を入力するだけで、元映像とフレーム単位で一致したアルファマットを生成。

グリーンスクリーン、マスク、プロンプトは不要。

[Aharon Rabinowitz @ABAOProductions]

Any compositor who looks at this and says I won't use a tool like this because it's AI is just stupid and self-sabatoging. There is nothing precious about green screen removal. There is nothing artistic about rotoscoping. It's painful, costly, time consuming grunt work that almost nobody enjoys. And if you happen to be someone that does, do it in your own free time. No employer wants to pay for your me roto time.

Speaking as someone who has done literally hundreds of hours of roto, its about freaken time. https://t.co/fC3AZtcAB4

[Stable Diffusion Tutorials @SD_Tutorial]

LTX-2.5 IC-LoRA Alpha Gen

takes an ordinary RGB video and generates a matching alpha matte for it, with no green screen, masks, or prompt required. It handles hard subjects as well as soft and semi-transparent elements such as hair, fur, smoke, fire etc

https://t.co/o8tQe00cze

[AmirMušić @AmirMushich]

Video background removal (RGB/Alpha smart split)
Tested on a dozen of my videos - works precisely

Right in your browser. Damn, that's good
Save this damn tool for future, thank me later

[Tom Factor @tom_factor]

@Yokohara_h 🔥

[LTX.io @ltx_io]

The last drop of VFX Week: Alpha Gen (Beta).

Give it an ordinary RGB clip and get back an alpha matte that matches your plate frame for frame. No green screen, no masks, no prompt.

Built for the edges that are hard to key or roto: hair, fur, smoke, fire, glass, water. 🧵

[LTX.io @ltx_io]

Layout to Render (Beta) drops today.

Your 3D blocking transforms into a finished shot.

Set your composition in 3D and LTX generates the surrounding environment, holding strict alignment with your CG. Shape the visual treatment using a prompt or reference image without altering your established framing.

Start from your current layout today.

[Victor Perez @vctrprz]

LTX 2.5 in an ACES pipeline: Nuke → ComfyUI → Nuke.

Watch: https://t.co/XoGAiCABH5
LTX for VFX: https://t.co/9MlhGSxgr9
HuggingFace: https://t.co/weCviMl9jy

[LTX.io @ltx_io]

VFX Week drop two. First we have the updated SDR to HDR.

Most AI video tools hand you 8-bit files. They look fine on a phone, but your colorist has nothing to push.

SDR to HDR turns 8-bit footage into 16-bit EXR in ACEScg and rebuilds highlight and shadow detail for the grade. 🧵

[Doug Hogan @heydoughogan]

As a Nuke Compositor, one of the strangest things about working in generative AI (and there's been a few) has been producing visuals who's pixel range isn't maintained throughout the process. We're training as VFX artists to preserve that pixel data at all costs, but until now...it just wasn't possible in genAI because how these diffusion models were trained.

Well now those days are over! If you have HDR footage and you need to do some generative work on it...your pixels will be maintained end to end!

This is huge! Great work to the entire https://t.co/Kw1EYc2KJU team!

[LTX.io @ltx_io]

Restore is for archival footage.

Take a 540p clip to 4K. Restore enhances color and adds a clean, sharp finish, as if the footage came off a modern digital camera.

Refine keeps a shot faithful to the source. Restore changes the look intentionally.

[LTX.io @ltx_io]

VFX Week starts tomorrow. We're dropping new VFX capabilities every day this week.

Built for your comp, your grade, your final delivery.

Each one is built into your pipeline. Not as an add-on, but as part of how you work.

Follow along all week.

[LTX.io @ltx_io]

Once the shot works, you should not have to start over just to fix the light.

Our Relight IC-LoRA gives you another pass at the mood after the generation exists.

[Mohamed Oumoumad @MedOumoumad]

A tiled workflow I've been developing for a while with @ltx_io's LTX 2.5 pushes the model way past its native resolution.
These are results of random T2V/I2V 1080p videos upscaled to 8K.

[Yao Zhang @YaoZhangX]

LTX 2.5 JUST WENT FASTER THAN REAL TIME

LTX (@ltx_io) is already one of the world's most widely used open video models. We just made its latest release, LTX 2.5, fast enough for rapid iteration and affordable enough for production at scale. 

It’s live on @TensorScaleAI now, generating a 5-sec 1080p video in just 3.12s at $0.04 per second. That's faster than real time, at a fraction of the cost!

For creative teams, that means less waiting time, more ideas explored, and lower production costs.

For robotics and physical AI teams, that means more data generated at scale, more scenarios tested, and shorter development and deployment cycles.

Request early access today and we’ll get you onboarded!
(link: https://t.co/0PAXBDiNir)