Sylvain Filoni
3.5K posts
Sylvain Filoni
@fffiloni
🇫🇷 Fellow ML Imagineer @huggingface 🤗 • Master Animation Film | VFX • @psl_univ @ecole_artsdeco
Paris Katılım Kasım 2009
983 Takip Edilen7.5K Takipçiler
@julien_c Returning to ML after paternity leave, while supporting my wife through breast cancer, feels like this. I couldn’t agree more. 🎢🤘
English
Be like that cat, and lean in to it
Yuchen Jin@Yuchenj_UW
Man suffers only because he takes seriously what the gods made for fun.
English
Did you like @victormustar’s DLSS 5 Anything @Gradio Space? 🧨
Now, HF Pro users can run batch image enhancement using @HuggingFace Jobs 🤗
Try it: huggingface.co/spaces/fffilon… 🪭
AK@_akhaliq
DLSS-5 anything for free app: huggingface.co/spaces/victor/…
English
Sylvain Filoni retweetledi
You’ll open-source every of your research code and papers on @huggingface then, right ?
GIF
Adobe@Adobe
Today, Adobe and @nvidia announced a strategic partnership to reinvent creative and marketing workflows with the power of AI. Adobe’s creative and marketing technology, combined with NVIDIA’s research and accelerated computing, will come together to develop next-generation Firefly models and creative, marketing, and agentic workflows to deliver best-in-class creative precision and control. Check out the full announcement from #NVIDIAGTC to see what’s ahead: adobe.ly/3NszP6W
English
Curious about how DLSS-5 will work with dalle-mini outputs 😅🔥
AK@_akhaliq
DLSS-5 anything for free app: huggingface.co/spaces/victor/…
English
DALL·E mini is back 🤖🎨
still weird. still fun. 🤗
Try it:
huggingface.co/spaces/fffilon…
English
I’ve seen that many folks were missing Dalle-mini on HF 🥲 So i made a quick Gradio version you can duplicate 🤗 huggingface.co/spaces/fffilon…
English
Sylvain Filoni retweetledi
💚🤗💚 Jensen showing @huggingface during GTC keynote, where @NVIDIAAI dropped amazing new open models, datasets and blogs!
Some of my favorites, links in comments:
🧠 Nemotron 3 Super 120A12B - Reasoning LLM
🏥 Open-H-Embodiment - Healthcare Robotics Dataset
🩻 Cosmos-H-Surgical-Simulator - World Foundation Model
🚕 Alpamayo 1.5 - Autonomous Vehicle Model and Datasets
🕺 Kimodo v1 - Generate body movement from prompts!
And SO MUCH MORE to explore at huggingface.co/nvidia/collect…
English
Golden times for Indie game devs ahead 🤗
NVIDIA GeForce FR@NVIDIAGeForceFR
Nous annonçons le NVIDIA DLSS 5, une avancée majeure alimentée par l’IA qui franchit un nouveau cap en matière de fidélité visuelle dans les jeux, disponible cet automne. Le DLSS 5 enrichit chaque pixel avec un éclairage et des matériaux photoréalistes, réduisant ainsi davantage l’écart entre le rendu et la réalité.
English
The moment i figured it out about FOMO on AI 🤗
MOVie aREnaS 🌐@moviemindarenaS
The moment he figured it out
English
"You can even spawn Godzilla or summon a tsunami via text prompts."
Wait.. What ?
DailyPapers@HuggingPapers
Seoul World Model Navigate the real streets of Seoul for kilometers without leaving your screen. This city-scale world model uses retrieval-augmented generation to ground every frame in actual street-view data. You can even spawn Godzilla or summon a tsunami via text prompts.
English