NVIDIA's PiD is a new pixel diffusion decoder for... high-res image models. It skips decode-then-upscale stop, making sharper outputs faster. > Directly generates 4K images > Up to 5.9x faster than SeedVR2 > Free & open weightsshow more

NVidia just released PiD: super resolution in pixel space... directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Imageshow more

Diffusion models are sensitive to small changes in the... input noise. We introduce Alias-Free Latent Diffusion Models (𝗔𝗙-𝗟𝗗𝗠) at #CVPR2025. It achieves shift-equivariance and generates consistent outputs. Project: arXiv:show more

Switti -- a new scale-wise transformer for text-to-image generation... 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.show more

Hindi Speech Model should be free and open-source. And... we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!show more

Here's the result of Codex 5.3 ! > Upload... a reference animation (IDLE) > Prompt what new animation you want > Sends image + prompt to Nano Banana Pro > Generates new animation sprite sheet The app looks good and functions well! > Next.js 16.1 > Convex dbshow more

Just a couple of prompts from start to finish... into a playable game! Pixel-perfect art > Codex App w/ GPT 5.5 High > Images 2.0 for animations (except walkcycles) > WAN 2.0 for walkcycles (cheap!) > 11Labs for bgm/sfx (in 1 prompt) > Phaser 4 Sound ON🔉 Full tutorial anyone?show more

Kartikeya temples: Kangra, Pehowa, Uttarakhand, West Bengal, Ahmedabad… list... is endless 🥵 Standing tall while modern “influencers” collapse faster than their WiFi. Heritage >>> hype.show more

Nano Banana 2 is live on Arcads > Faster... generations > Better text rendering > Higher consistency Try todayshow more

Trained a simple world model for my robot arm.... It predicts the future over 20000 times faster than real time on a single NVIDIA RTX 3090 GPU (128 batch -> 160x faster each).show more

Making the 50/50 “reactable” for a tricky mix-up >>>>

>cranking laser musket >see deathclaw running at me >cranks... laser musket fastershow more

1. nano banana is great for editing images go... to Canvas -> Nano Banana -> upload image -> upload product swap face, hold product, change clothes.. and use Veo3 or Kling 2.1 to generate video it's free and unlimited for 24h now link:show more

Bytedance just dropped realtime voice translation 3x faster than... before, with only a ~3s lag! Seed LiveInterp 2 is a full duplex speech-to-speech model with >70% correctness. When this makes it to video calls, it'll open up previously impossible connections.show more

Damn it worked! Genie 3 world --> inpaint UI... --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any image-to-3d model I've seen. I think Google has stumbled upon the killer app for VR -- the literal holodeck.show more

text to film AI is coming faster than you... imagine this new OpenCreator AI can turn your simple idea into film clips with one click, idea -> script -> storyboard -> video all on its own and.. the node based canvas make it even more professional step by step tutorial:show more

you can now generate prompts from images in Krea... drag & drop any image into the prompt box -> get a prompt for itshow more

Selected as a best paper finalist at #CVPR2026: PixelDiT... from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.show more

Love when the high low is executed from a... big to a guard >>> Kalani Brown dishes it off to Celeste Taylor 🫡 LVA-PHX | Watch FREE on the WNBA APPshow more

Lifting weights at 3am>>>

We're releasing OVIE, a novel view generation model trained... entirely on single images. No multi-view datasets needed. Given a single image, it generates novel views of any scene in real time, running orders of magnitude faster than competing approaches.show more