playing with Wan 2.2 for t2i. funny results when using Smartphone lora to upscale and detail, it turns everything to realistic style

JUST IN: 🇺🇸 US Department of Commerce partners with Chainlink $LINK to bring "government macroeconomic data onchain."

Tencent just open-sourced HunyuanVideo-Foley: a model that generates sound effects directly from video One step closer to open models with native audio like Veo 3!

time travel is here.. this app lets you revive past memories in mixed reality.. insane wizard 👉 wistlabs .com

Termiflanero

This is amazing

Restyle of the classic #akira bike in cybernetic style civitai.com/images/1052583… a través de Civitai

Today it's leather time civitai.com/images/1064409…

InfinityStar by Bytedance: A unified 8B spacetime autoregressive model for high-res image & video gen; - 5s 720p video ~10x faster than DiT; - scores 83.74 on VBench, topping other AR models and HunyuanVideo; - Flan-T5-XL as text encoder. - 480/720p, ~35Gb model

Vamos Colapinto hoy #43

🚨🇪🇺 ECB QUIETLY UNVEILS THE FINAL CHAIN: DIGITAL EURO LOCKDOWN BY 2029 In what central bankers are celebrating as the “crowning evolution of money,” the European Central Bank just confirmed the irreversible rollout: a fully trackable, programmable digital euro arriving no later

🚨 800 FREE CREDITS — 24 HOURS ONLY We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync. Follow + Retweet this post to get 800 credits sent to your DMs.

The United Nations wants you to forget that Ghislaine Maxwell was invited to speak as an "expert" at the UN on multiple occasions.

Tendencias ARG Acá el vídeo recreando la mega estafa de Libra con la participación estelar de Javier Milei: #libra

NVIDIA says: no more "brute force every pixel" of video understanding. AutoGaze- identifies and removes redundant video patches before they enter a Vision Transformer. Now we can processes 4K long-video in real-time. Works with SigLIP2 and NVILA. autogaze.github.io

I trained this LTX LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)