Disarm, grow, change, and start over

NeuralOS: a generative OS entirely powered by neural networks

NeuralOS, probably the world's most expensive operating system, running at a blazing 1.8fps on an NVIDIA H100 GPU. 😅

What exactly is NeuralOS?

It's an experimental generative OS that predicts every screen frame entirely from your mouse and keyboard inputs. No internet, no traditional software stack, purely hallucinated pixels.

How does it work?

- An RNN tracks the computer state (kind of like a traditional OS kernel, but all neural and continuous).
- A diffusion model generates the actual screen images (imagine a desktop environment, but fully neural-rendered).

The GIF shows a funny demo: NeuralOS running NeuralOS inside itself. Every single pixel you're seeing is model-generated, no network involved at all!

Long-term, our goal is to remove boundaries between software entirely and make OS fully customizable beyond fixed menus and options. Imagine asking your OS something like:

- "Merge all my messaging apps into one interface."
- "Make Signal look like Messenger."
- "Turn the movie I'm watching into a playable video game."

I'm curious about your thoughts:

Could future OS interfaces just become human-like avatars (think Grok's Ani)? Are menus and app-specific UIs going away?

What about fully generative games: could diffusion-based games eventually replace traditional ones?

Try the live demo here: neural-os.com (you might need patience…)

Logo reveal in ink-in-water style with VEO3 🖋💧

Runway Aleph can accurately remove subjects from your scene. Even with complex motion, lighting conditions and passing foreground occlusions. All you need to do is tell Aleph what you want.

Update in @neuralforum Chat

We are pleased to announce that a new image generation model, GPT-4o, is now available.
Other models such as DALL·E 3 and Google Gemini Images remain accessible as well.

How to use:

/o prompt → Generate images with GPT-4o

/i prompt → Generate images with DALL·E 3

/g prompt → Generate images with Google Gemini

👉 The bot is available in this topic:
https://t.me/neuralforum/7333097

✅ All requests are free and unlimited.

Update in @videotoanimebot

The bot now supports modern animation styles!
Transform any photo into:
🌿 Studio Ghibli
🎬 South Park
💛 Simpsons
🌸 Anime
🎥 3D Pixar
🎨 MS Paint
📷 Vintage
🟦 Pixel Art (Pop Art)
🪵 Wooden Doll
🧶 Knitted Doll

In addition, the bot also offers:
✍️ Creative Writing from Images (poems, stories, stand-up)
😂 Meme Generation
👕 Virtual Try-On

✅ All features are free and unlimited for everyone.

👉 Try it now: @videotoanimebot

About a robot that became a 3D printer! 🖨

A team of designers in Shanghai developed a groundbreaking 6-axis robotic 3D printer inspired by spiderwebs during a three-week summer workshop at Tongji University.

The project sought to merge design and fabrication processes, drawing from spider threads' biomimetic strength and structure. 🕸

The printer utilizes a unique spindle-knot extrusion technique, enabling self-supporting structures and greater spatial flexibility than traditional layer-based 3D printing.

The device features a robot from KUKA and a robotic end-effector with movable printheads, controlled by an Arduino-based system with precise temperature and extrusion controls.

Despite being a work in progress, the project exemplifies the potential of combining robotics and 3D printing for advanced manufacturing applications.

Generate persistent 3D worlds from a single image — bigger and better than ever!

The service has officially launched in limited beta, bringing the next step in world generation technology. From a single picture, you can now create fully persistent, explorable 3D environments that are larger, richer, and more immersive than before.

This beta marks the first public preview of the new model, and it’s designed to push the boundaries of creativity, design, and simulation. Whether you’re experimenting, building prototypes, or exploring new workflows, the experience is now available to try.

👉 Sign up for beta access here:
https://www.worldlabs.ai/blog/bigger-better-worlds

This is the best robotic hand I've ever seen.

Not even Tesla or Figure has been able to achieve this. The next 5 years are going to be crazy.

Alibaba's character swap via Wan2.2-Animate

very impressive and free and open-source..

GitHub:
https://github.com/Wan-Video/Wan2.2

HF Inference:
https://huggingface.co/spaces/Wan-AI/Wan2.2-Animate

Wan Video Inference (free, worked for me ~50% of time, slow):
https://wan.video

Shattered limbs? Jammed motors? If the bot can move, the Brain will move it - even if it’s an entirely new robot body.

Meet the omni-bodied Skild Brain.

Rick and Morty generated by Sora 2 my god

https://sora.chatgpt.com/

New update:
The Telegram bot now supports the MAI-image-1 model for image generation.
The model can generate square, vertical, and horizontal images.

How to use:
Send a prompt with the command /m, followed by one of the keys:
-s → square image
-v → vertical image
-h → horizontal image

Example:

/m -s a futuristic city at sunset

/m -h a futuristic city at sunset

/m -v a futuristic city at sunset

Public bot:
https://t.me/neuralforum/7333097

Several of our servers have experienced critical failures and are currently out of service. Because of this, some bots and certain features may not function properly or may be temporarily unavailable.

I’m already working on diagnosing the issues and repairing the damaged servers. The recovery process may take a few days, but I’m doing everything possible to restore stability and bring all bots back online as soon as I can.

Thank you for your understanding and patience during this downtime. If anything changes, I will provide updates.

Support\chat: @neuralforum