We present HeadHunter, a framework for principled analysis of perturbed attention guidance 🤖 Consequently, it enables deeply fine-grained control over the generation quality & visual attributes. Join in 🧵 for insights and "guidance". 1/12

I think Normalized Attention Guidance simply just fixed FLUX[dev] challenges with style 🤯

One of the most requested feature is now shipped on the Hub -> Filter Hugging Face Models by parameters count 🚀

just in case... huggingface.co/krea

this would make sense in so many dimensions, for both krea and the community imo - the open image community is looking for a "next gen" model, after Imagen 4, GPT-Image-1, Recraft v3, Reve, etc. - opening it up would foster a customization community: contronets, fine-tuning

Who's gonna take the next-generation open image generation crown? 👑 Both Reve and Recraft could be leading image generation now and be the top-of-mind imo. They could've 10-100x the impact of their "red panda" 🐼 and "halfmoon" 🌙 leading the charts... if they had open

this is not a drill 🚨, real-time open source video generation is here 🔥 Self-Forcing - a real-time video distilled model from Wan 2.1 by Adobe is out, and they open sourced it 🐐 I've built a live real time demo on Hugging Face Spaces 📹💨

LAION proudly presents 2 state-of-the-art emotion detection models for voice and face, surpassing Gemini 2.5 Pro and Hume API. They are completely open under a CC BY 4.0 license, alongside a ~5,000-hour voice-acting dataset & 2 expert-annotated benchmarks. laion.ai/blog/do-they-s…

So excited to welcome Google's model #1000 at Hugging Face: Magenta Real Time!🤯 🎷Music generation model ⚡️Real-time 👀Permissive license 🤏800 million parameters Model: hf.co/google/magenta… Blog: magenta.withgoogle.com/magenta-realti…