Latest news with #Lightricks
CNET
20-05-2025
- CNET
Test Out Hairstyles and Avoid Regret With This AI Tool
I'm a sucker for those '90s rom-com makeover movies, and whenever I'm getting my own hair done, I always envision that "big reveal" scene. But when I'm going to spend $400 plus tip to get a color and cut (a luxury experience in this economy), I want to be sure I'll love it. So I tried out Facetune, an artificial intelligence app that promises a collection of hair change images in seconds, to "try on" a few cuts and colors. At the very least, I'd have better photos to show my hairdresser during the consultation. Facetune is a product by AI company Lightricks, which was founded in 2013. You can use Facetune to change hairstyles, makeup, outfits, skin tone and facial hair, and as a "personal fashion stylist." There's a free and paid version of Facetune, including a seven-day free trial with access to all the premium features. So, Facetune, can I pull off bangs? Setting up Facetune's AI features I downloaded the Facetune app, accepted the terms and conditions. The Facetune interface is easy to navigate. I like its sense of humor, with options such as asking Facetune's AI assistant to "roast my style." I followed the prompts: 1. I toggled "I edit for personal use" but there are other options for influencers and businesses. 2. I set my photo and video editing experience to basic. 3. I selected my goal of "color hair" (ignoring the options to smooth skin, whiten teeth and clear blemishes). 4. I activated my free trial. (I also put a reminder in my phone to cancel before the due date, because it charges the $60 annual fee at once, not monthly.) 5. I had to give Facetune access to my photo library, then I selected the first photo to test run. No selfies needed! Like my AI headshots and baby face generator, the photo quality is critical. Pick a few photos where you're looking at the camera, hair down, without sunglasses on. Follow my golden AI rule: The better the input, the better the output. There are 36 color tones to choose from, but I decided to test only the ones I liked: blonde, brunette and pink (because I've been wanting to try that). I always feel better and more myself when I'm blonder. Maybe it's my skin tone or the fact that I'm from Australia, so my hair always had natural highlights. Now that I live in New York, and the seasons are distinct, I'm more inclined to explore color palettes. I wanted to see if Facetune could get close to my current color preference, which is a dark blonde. Here's the original photo: The "before" photo. Amanda Smith/CNET And Facetune's versions (gold tips and brown): Created by Amanda Smith using Facetune AI I liked both colors. They were natural looking, which is what I always aim for in my hair coloring. A second attempt with the AI hairstylist For the last picture, I wanted to test out its haircut capabilities. This time, I kept the color but went straight to the "hairstyles" option. Here's the original photo, and the various styles and cuts to choose from. Screenshot by Amanda Smith/CNET Facetune's "hair stylist" turned me into a '60s housewife, and I'm not mad about it. But this is when things started getting weird with my hand. Created by Amanda Smith using Facetune AI I noticed there was a text prompt feature under "Custom," so I asked the AI to make my hair like a 1960s hippie. Things got a tad weird -- both with my hair and whatever the AI tool did to my poor hand. Created by Amanda Smith using Facetune AI I still hadn't figured out if I could rock bangs, so that was my last prompt. Created by Amanda Smith using Facetune AI While I didn't hate it, I wasn't 100% convinced I could pull it off. Maybe I need to use different photos. Just when I was starting to feel game to try out a swept fringe look, this happened. It just wouldn't be AI without one super weird photo. My hand and chin are doing something even funkier than in the '60s hippie attempt. But I got to the end without a major glitch, so I was happy about that. Created by Amanda Smith using Facetune AI AI as a hairstylist: the verdict Facetune was a lot of fun to play with. I don't know if the color labels in the app are true to the hairdresser tones, but it does give the stylist a good starting point. Even if I don't feel comfortable divulging to my stylist that I used AI, it gives me a good sense of how I'd look, so I can search for similar pictures to present. I'll likely do the latter, unless my hairdresser best friend from home is doing my color, so we can have a good giggle about AI first. The Facetune app is super easy to set up and use, and it generates images in seconds -- with various complementary features that can boost your beauty confidence. You can do the same for makeup looks and clothing styles, but I wouldn't want to change my eye or skin color. That's just weird! Can Facetune save me money and embarrassment on the wrong hairdo? I bet. Do blondes have more fun? On Facetune, they sure do.
Malaysian Reserve
06-05-2025
- Malaysian Reserve
Lightricks Launches 13B Parameters LTX Video Model, Breakthrough Rendering Approach Generates High-quality, Efficient AI Video 30X Faster Than Comparable Models
JERUSALEM and NEW YORK, May 6, 2025 /PRNewswire/ — Lightricks , a leader in AI-driven content creation technology, today announced the release of its LTX Video 13-billion-parameter model (LTXV-13B) – which may be the most advanced and efficient AI video generation model to date. This substantial upgrade dramatically increases quality while maintaining LTXV's unparalleled speed generating AI videos. The 13B model is available within the company's flagship storytelling platform, LTX Studio, shared with the open community and is being integrated across the Lightricks portfolio. LTXV-13B introduces 'multiscale rendering,' a major technical breakthrough that delivers both speed and quality through a layered process. The model drafts in lower detail first to capture coarse motion using fewer resources. This draft then guides the next stages, where the model progressively adds structure, lighting, and micro-motion (and spending time where it matters most). The result is high-fidelity video built through deliberate, multi-scale generation, with render times that can be more than 30X faster than comparable models – without compromising visual realism. The new 13B model represents a significant leap forward in Lightricks' generative AI capabilities, offering creators the ability to produce videos with stunning detail, coherence, and control. It utilizes the latest advancements in academia and the open source community, including unsampling controls and spatiotemporal guidance for video editing, and kernel optimization for running speeds. Unlike other models that demand enterprise-grade GPU (and long rendering times), LTXV-13B delivers studio level video at unmatched speed, even on devices that creators already own, which differentiates LTX Video in the marketplace. 'The introduction of our 13B parameter LTX Video model marks a pivotal moment in AI video generation with the ability to generate fast, high-quality videos on consumer GPUs,' said Zeev Farbman, co-founder and CEO of Lightricks. 'Our users can now create content with more consistency, better quality, and tighter control. This new version of LTX Video runs on consumer hardware, while staying true to what makes all our products different – speed, creativity, and usability.' While developing and refining the 13B model, Lightricks entered into a strategic partnership with leading media asset provider Getty Images . In December 2024, Lightricks entered an agreement with Shutterstock to leverage their licensed content. These kinds of collaborations have given Lightricks access to an extensive library of high-quality video assets for model training, reinforcing its mission to build ethically trained, visually compelling, and commercially safe generative tools. The LTXV-13B model now empowers creators with even more control and flexibility, seamlessly supporting all of the platform's advanced creative tools, including: Keyframe editing Camera motion control Character and scene-level motion adjustment Multi-shot sequencing and editing In support of startups and small businesses, Lightricks is offering the 13B model free to license for enterprises with under $10 million in annual revenue. This initiative and the release of all LTXV models in open source reflect Lightricks' commitment to making cutting-edge generative AI accessible to the next generation of creative companies and innovators. Open source versions of LTXV are available on Hugging Face (LTX-Video) and GitHub (LTX-Video) . 'By consistently refining our models and working with the open community, we've built an AI system that generates physically natural movement while preserving artistic control,' added Yoav HaCohen, Director of LTX Video at Lightricks. Since launching LTX Video in November 2024, Lightricks has collaborated with researchers and open-source contributors to improve motion consistency, scene coherence, and creative adaptability. Key open-source advancements in LTXV-13B include: VACE Model Inference – advanced video generation and editing tools, including reference-to-video (R2V). Details on GitHub – advanced video generation and editing tools, including reference-to-video (R2V). Details on Unsampling Controls for Video Editing – Tools that reverse noise and refine frame granularity. Details on GitHub . – Tools that reverse noise and refine frame granularity. Details on . Kernel Optimization – Efficient Q8 kernel usage allows performance scaling on lower-resource devices. Details on GitHub and HuggingFace . With a growing library of models designed for diverse creative needs and a commitment to open development, Lightricks is shaping the future of generative AI video, bridging research-driven breakthroughs with real-world application. For more information about Lightricks, its products, technology, and open-source initiatives, visit . View original content to download multimedia: SOURCE Lightricks
