Jean Santana

Agora é sua vez Playstation

@ltx_model Why we are talking about HDR if we even't cant generate accurate emotional scenes consistent with reality yet?

@ltx_model I think the gap is still consistency across scenes, it worth nothing if I generate a video with audio and in the next scene the voices changes.

LTX-2.3 is a major upgrade. It’s a production-ready multimodal engine - designed to be built on. Here’s what’s new 🧵 1/7

@FireWoGames Yes, I do want this. When it will be released?

YOU WANT THIS GAME! YOU KNOW IT, I KNOW IT, EVERYBODY KNOWS IT

@jerrod_lew Try a crying scene please, all video models today struggles to deliver crying scenes.

Runway Gen 4.5 has launched Image-to-Video. Upload any image to combine with a text prompt to guide your output. Videos are up to 10 seconds long. This is really impressive, and shows the power of the latest 4.5 model with expressions, actions and camera movement.

@jan_rosner Now I just ask, Why??? Why YOU GUYS don't release a VR official mode in the game? You see that so many want this and even would pay for it, but no, you guys just don't care at all.

I’d like to briefly address the discussion around the “Cyberpunk VR” mod created by Luke Ross. We have indeed issued a DMCA strike, as it was available as a paid mod (only accessible to Patreon subscribers). This directly violates our Fan Content Guidelines: we never allow monetization of our IP without our direct permission and/or an agreement in place. We were in touch with Luke last week and informed him that he needs to make it free for everyone (with optional donations) or remove it. We are big fans of mods to our games — some of the work out there has been nothing short of amazing, including Luke’s mod for Cyberpunk 2077. We’d be happy to see it return as a free release. However, making a profit from our IP, in any form, always requires permission from @CDPROJEKTRED. You can find our full fan content guidelines here: cdprojektred.com/en/fan-content

@flaviogarag E você está contribuindo para isso, e olhe lá se esse não for seu objetivo. Cada pessoa que compartilha está contribuindo para o que você está falando.

Estão preparados pra ver essa aqui ganhar mais dinheiro do que você que estudou pra caralho?

@runwayml Is this model capable of show people crying without look like a gelly fountain coming out of the eyes?

Explore every world. Tell any story. With Runway Gen-4.5, available now.

@paulodetarsog “Estava em surto” merda nenhuma! O tempo todo é por toda parte esses valentões dão as caras e querem violência gratuita em qualquer situação.

Palmas, Tocantins. O cara executou um segurança do mercado, desarmado, porque foi reclamar com ele que não poderia estacionar a sua caminhonete de luxo num determinado local. Este é o retrato de uma geração mimada que não suporta ser contrariada.

@LTXStudio The day LTX be able to keep consistent actor voices, this will be a game changer.

While everyone's hyping effects, Nano Banana Pro in LTX solved character consistency across angles. → Native 4K → Native lipsync NB PRO 🤝 LTX-2

@icreatelife nano banana pro + @grok + my own production

Share your AI experiments with Nano Banana Pro

@GoogleAI It still generates with the watermark even if it says that is nano banana pro

Rolling out today we are launching Nano Banana Pro, the world’s best image model built to move beyond casual creation and into a new era of studio-quality, functional design. Nano Banana Pro enables a new level of precision and creative control, transforming the way you bring ideas to life. Here are a couple of our favorite new features: — Text rendering and translation: Generate crystal-clear text directly within your images. With the model’s advanced language understanding, you can even translate and regenerate visuals with localized text. — World knowledge: By connecting to Search’s vast knowledge base, Nano Banana Pro generates factually accurate diagrams and realistic product placements, making it an invaluable tool for learning and communication.

@GeminiApp Common Google, focus on improve model fidelity audio consistency, dramatic scenes.

We’re back with another update to Veo 3.1: Rolling out now on mobile and desktop, you can upload multiple reference images alongside your video prompts, to create entirely new worlds and more nuanced videos that are true to your vision.

@elonmusk @elonmusk All AI models today fails when comes to unleash the human creativity for videos. Models are failing on generating dramatic scenes and prohibiting many things. Please make grok allow us to create art without boundaries.

Imagine when Grok does this in real-time for an AI game

@LTXStudio Awesome! Can’t wait for that. Do you guys plan let it open source this month?

@jeansefan_dev Characters yes, if you start with an image. Voices - we’re working on this.

Can you last 20 seconds? We can... LTX-2 Fast delivers long takes with synced audio and native lipsync. It gives you more space for dialogue, smoother pacing, and more flexibility within a single generation. Here’s how it works (Prompts+Tips+Examples) 🧵

@GeminiApp You guys should stop limiting the creativity to tell stories. Google refuses any thing that is about death, depression, or thing that are common in human life. If you try, veo mute sounds, refuse generation. If a AI is just to create idiot slops, so there is no purpose.

Halloween is here, and people are using Gemini to get in the spooky spirit. From chilling videos to silly costumes, see some of our favorite recent creations: 🧵

@LTXStudio You guys plan to make possible extend so it keep consistent characters and voices across scenes?

20 second generations just dropped in LTX. You can now generate up to 20 seconds of continuous video with synced audio, motion, and character performance. Available with LTX-2 Fast. One shot. One take 👇

@machina9000 How you make the audio voices consistent across characters?

Updated version of Zephyria-7

@EthanHe_42 @grok Something that you guys should pay attention is the crying scenes. For some reason 99% of AI models out there including grok, is not possible to generate realistic crying scenes. Also please fix this "drawing" look for realistic people.

7 minutes short film made with @grok Imagine