Sylvain Filoni's picture

Sylvain Filoni

fffiloni

AI & ML interests

ML for Animation • Alumni Arts Déco Paris • PSL

Recent Activity

updated a Space about 11 hours ago
fffiloni/llm-from-image
updated a Space about 11 hours ago
fffiloni/MEMO
View all activity

Organizations

Notebooks-explorers's profile picture AI FILMS's profile picture Prodia Labs's profile picture Hugging Face Fellows's profile picture Nanomenta ML's profile picture temp-org's profile picture Blog-explorers's profile picture huggingPartyParis's profile picture The Collectionists's profile picture ZeroGPU Explorers's profile picture Workshop ENSAD DG's profile picture Gradio Templates's profile picture ENSAD DO's profile picture INNOVA AI's profile picture Social Post Explorers's profile picture Top Contributors: Space Likes's profile picture Top Contributors: Profile Followers's profile picture Telescope Optique Unterlinden's profile picture Dev Mode Explorers's profile picture Nerdy Face's profile picture

fffiloni's activity

New activity in fffiloni/DiffuEraser-demo about 12 hours ago
upvoted an article 2 days ago
view article
Article

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

By Kseniase
288
reacted to cbensimon's post with 🚀 2 days ago
view post
Post
2764
🚀 ZeroGPU now supports PyTorch native quantization via torchao

While it hasn’t been battle-tested yet, Int8WeightOnlyConfig is already working flawlessly in our tests.

Let us know if you run into any issues — and we’re excited to see what the community will build!

import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_

pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)

@spaces.GPU
def generate(prompt: str):
    return pipeline(prompt).images[0]
·