Tabea.Edelstein

Interessiert an Lehre und Lernen, Grundschule, rein privater Account

[fal @fal]

We just open-sourced 3DREAL !

A new render-to-real IC-LoRA for LTX-2.3 from fal: turn any 3D / CG / game render into high 3d render, photorealistic, film-quality video, keeping your exact composition and camera move using the first frame.

[Xenova @xenovacom]

Massive congrats to the @PrismML team on the release — truly a game-changer!

For those interested, we load the MLX weights and use custom WebGPU kernels for inference. Also, the animated Bonsai landing page was prototyped with @omma_ai

🔗 Link to demo: https://t.co/Jff4xI4yKH

[Google for Education @GoogleForEdu]

Moodle users, we’ve got news for you 📰

Gemini LTI now supports @Moodle with tools like the @GeminiApp and @NotebookLM. That means easier lesson planning and smarter study tools right in your LMS.

Set up your school today: https://t.co/Q04bZnBQcb

[Sundar Pichai @sundarpichai]

You can now ask Gemini to create Docs, Sheets, Slides, PDFs, and more directly in your chat. No more copying, pasting, or reformatting, just prompt and download.

Available globally for all @GeminiApp users.

[Olivia Chowdhury @Oliviacoder1]

GOODBYE CAPCUT 👋

Gemini can now script and edit full videos in minutes.

No dragging timelines. No manual cuts. No creative blocks.

Here are 7 prompts to make it happen 👇🏽

[Claude @claudeai]

Claude now connects to the tools creative professionals already use.

With the new Blender connector, you can debug a scene, build new tools, or batch-apply changes across every object, directly from Claude.

[Serus @serus_ai]

With Serus, you can scan +100 billions of dark web records and find exactly what information has been leaked about you.

Passwords. IP-Addresses. Phone numbers. Emails. All of it.

Takes seconds. Hits hard. Try it out, for free.

[Matthew @TzDev_]

https://t.co/jRRH5MZaPQ

[Oliver Prompts @oliviscusAI]

someone built a tool that turns any google maps link into a fully 3d gaussian splat.

you just paste the url and it generates an immersive 3d scene instantly.

it’s 100% free..

[Ideogram @ideogram_ai]

Today, we're introducing Editable Text Layers and Design Categories.

Your copy is now its own layer. Rewrite it. Restyle it. Resize it. The image underneath stays exactly as it was.

Available to all users for free, and accessible via the API.

[Oogie @oggii_0]

Bullet time effect using Seedance 2.0 on @SocialSight

Prompt: Bullet time effect. A businessman in white shirt and black tie slipping and falling backwards on an icy wet street in Wall Street, New York. Coffee cup standing on ground, liquid exploding outward frozen in mid-air. Ice chunks, water droplets, and coffee splash all completely suspended time is frozen. Tall buildings on both sides creating a canyon effect. The camera smoothly orbits 360 degrees around the falling man at low ground level angle, only the camera moves while everything else remains perfectly still. Cinematic, overcast dramatic lighting, wide angle lens distortion.

[Kanika @KanikaBK]

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE.

It knows who spoke.
It knows when they spoke.
It knows exactly what they said.

All in one shot. No chunking. No context loss.

It's called VibeVoice.

Not a transcription tool.
Not a basic speech to text wrapper.

A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free.

Here's what it actually does 👇

VibeVoice ASR - Speech Recognition:
→ Processes 60 minutes of continuous audio in a single pass
→ Never slices audio into chunks so global context is never lost
→ Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously
→ Supports customized hotwords for domain specific accuracy
→ Works in 50+ languages natively
→ Already adopted by Hugging Face Transformers library
→ Already being built on by the open source community

BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE.

VibeVoice TTS - Text to Speech:
→ Generates up to 90 minutes of speech in a single pass
→ Supports up to 4 distinct speakers in one conversation
→ Natural turn taking and speaker consistency throughout
→ Expressive speech that captures emotional nuances
→ Supports English, Chinese and multiple other languages

VibeVoice Realtime - Streaming TTS:
→ Only 300 millisecond first audible latency
→ Streams text input in real time
→ 0.5B parameters so it actually deploys anywhere
→ Robust long form generation up to 10 minutes
→ Lightweight enough for production use today

The core innovation nobody is talking about:

Most voice AI models slice long audio into short chunks.
Every time they slice, they lose context.
Speaker tracking breaks. Semantic coherence breaks. Accuracy drops.
VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz.
This preserves audio fidelity while dramatically boosting computational efficiency.

The entire 60 minutes stays in context.

Nothing gets lost. Nobody gets misidentified.

The numbers:
→ VibeVoice ASR 7B - available now on Hugging Face
→ VibeVoice Realtime 0.5B - try it on Colab right now
→ 50+ supported languages
→ 11 distinct English voice styles
→ 9 multilingual speaker voices
→ Already integrated into Hugging Face Transformers
→ Finetuning code now available

The wildest part?
A voice powered input method called Vibing just built itself on top of VibeVoice ASR.

Available on macOS and Windows right now.
The open source community is already shipping products on top of this.

100% Open Source.
Free to use. Free to fine tune. Free to build on.

🔖 Save this before your competitors find it first. 👇

[NotebookLM @NotebookLM]

Last year, we integrated into the @GeminiApp by allowing you to upload your notebooks as sources. Now, we’re taking our relationship to the next level 🏠 ♥️

Starting today, you can now:

— Access all of your personal, unshared notebooks directly inside the Gemini App
— Use your chats with Gemini as sources in new or existing unshared notebooks

We're rolling out notebooks in Gemini today, starting with Google AI Ultra, Pro, and Plus subscribers on the web. In the coming weeks, we'll expand access to mobile, more countries across Europe, and to free users.

[Daily Dose of Data Science @DailyDoseOfDS_]

The first truly open-source audio-video model.

LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model.

Designed to run locally on consumer GPUs.

- text-to-video
- image-to-video
- and video-to-video modes

100% open-source.

[Will Eastcott @willeastcott]

The real estate sector is NOT ready for this. 🏠💥

Forget static photos and clunky 360 tours. You can now freely explore photorealistic digital twins of homes in your browser.

The new "Walk Mode" in @PlayCanvas SuperSplat just changed the game. 🧵

[Olivia Chowdhury @Oliviacoder1]

Google’s NotebookLM just turned into the most dangerous, unfair content weapon no one is talking about.

You can instantly reverse-engineer any viral YouTube channel and clone its entire content system in under 60 seconds.

7 prompts. Zero guesswork. Pure content domination. 🧵

[Wildminder @wildmindai]

A client hands you a single, cluttered photo of their living room and asks what it would look like rearranged.

> feed the flat 2D photo into the framework
> it pulls every piece of furniture into a separate 3D asset
> auto-completes the hidden sides of the sofa
> builds a clean, empt 3D room underneath
> snaps everything perfectly to the floor plane
> drag, drop and redesign the entire space in minutes

Hunyuan3D 2.0 + VGGT + NBpro

https://t.co/dbsR5dEodG

[Amira Zairi @azed_ai]

Really interesting to see where this is going.

If you want to test it yourself, you can check out OpenArt Worlds here

https://t.co/s48mZWXDSq