Recently finished writing a new blogpost about @PyTorch compilation in ZeroGPU Spaces. Worth reading if you're interested in learning about : - PyTorch ahead-of-time compilation - ZeroGPU internals https://t.co/Jk3IwBlqEE

new button who is this

try it here https://t.co/bxnq7djyNs

no last frame? no problem added a new button to the wan 2.2 first-last frame demo 👀

Im having so much fun with this https://t.co/eLJOP2zBJj

(made with nano banana of course https://t.co/AUpt6WSjMl)

good morning, be gentle with yourself 🌼

Kimi K2-0905 update 🚀 - Enhanced coding capabilities, esp. front-end & tool-calling - Context length extended to 256k tokens - Improved integration with various agent scaffolds (e.g., Claude Code, Roo Code, etc) 🔗 Weights & code: https://t.co/83sQekosr9 💬 Chat with new Kimi

i’ll stop to generate boba teas soon

a medium sized boba tea please

don't try this at home

imagine if there was a Wan 2.2 version coming 👀

hey @Alibaba_Qwen, is that you?  "a photo of a capybara with a plain purple t-shirt wearing glasses using a computer"

"a photo of a man wearing a bad totoro costume eating pizza"

gosh, this model is something else "a woman drinking an iced boba tea in a beach in Rio de Janeiro"

@huggingface https://t.co/baNWMyag2f

this first experimental alpha version is available on @huggingface, prompt it like "a photo of [...], flikr photo from 2012" https://t.co/1KwZDUONjM

early results for the Qwen "Boring Reality" LoRA 📸 by kudzueye the model is still experimental and work in progress 🚧

we hacked Wan 2.2 and discovered that it does first and last frame filling, works out of the box on 🧨 diffusers i've built an app for it on @huggingface Spaces (which is powering powering our nano banana video mode too 🍌 🎬)