Sylvain Filoni PRO
fffiloni
AI & ML interests
ML Imagineer • Alumni Arts Déco Paris • PSL [Paris Sciences & Lettres] • HF Fellowship of Open-Source AI
Recent Activity
updated a bucket about 2 hours ago
fffiloni/hf-radio-likes updated a collection 3 days ago
LipSync and Face Operations liked a Space 3 days ago
victor/LongCat-Video-Avatar-1.5Organizations
A collection of my Hugging Face Spaces featured as Space of the Week or highlighted by the Hugging Face team.
-
Attention Is All You Need
Paper • 1706.03762 • Published • 122 -
Attention Residuals
Paper • 2603.15031 • Published • 185 -
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 80 -
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Paper • 2603.15557 • Published • 29
To-do: switch to HF Kernels
-
Kolors IP-Adapter
🖼160Create images from text and reference photos
-
InstantStyle
👁454Style-Preserving Text-to-Image Generation
-
Flux IP Adapter
🖼170Prompt with Images in flux[dev]
-
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Paper • 2411.15466 • Published • 39
All the steps to train your own SD-XL custom model
A collection of all papers referenced in OpenAI's "Video generation models as world simulators" technical report • openai.com/sora
How Text-to-Image evolved on HF and inspired the Community
Demos I published that had significant impact, in order of publication
How ControlNet grew and shined on HF
All my demos involving video in or out
All the bricks you might only need to combine for great AV understanding
-
SALMONN Audio Questioning
⚡83Deeply interrogate audio file content
-
NVILA HD Video + AutoGaze
🎯9Long video understanding with smart attention
-
TIGER Audio Extractor
✂119Extraction & Reconstruction for Efficient Speech Separation
-
Scene Edit Detection
✂20Detect and split video scenes into separate clips
-
DLSS 5 Anything Batch Jobs
🪭2Launch batch images enhancements with HF Jobs
-
DALL·E mini via Hugging Face Jobs
🎨1DALL•E mini batch Jobs
-
Text2Any Batch with HF Jobs Orchestration
🧨3Launch and monitor Hugging Face inference jobs from a web UI
-
AudioLDM2 Batch with HF Jobs
🧨Launch and monitor audio generation jobs
Research demos rebuilt for clarity, exploration, and better understanding of AI models.
Progressive list of MCP server ready trending spaces maintained by fffiloni
A collection full of musical tasks demos, for musicians & music enthusiasts
An ongoing collection of games you can play on HF Spaces
All spaces made to convert a video (of GIFs) to anything useful in your pipelines
All my demos involving music
No crazy stuff, but useful ones for in-between steps
Everything you need to reproduce my Music-to-Image demo
All the bricks you might only need to combine for great AV understanding
-
SALMONN Audio Questioning
⚡83Deeply interrogate audio file content
-
NVILA HD Video + AutoGaze
🎯9Long video understanding with smart attention
-
TIGER Audio Extractor
✂119Extraction & Reconstruction for Efficient Speech Separation
-
Scene Edit Detection
✂20Detect and split video scenes into separate clips
A collection of my Hugging Face Spaces featured as Space of the Week or highlighted by the Hugging Face team.
-
DLSS 5 Anything Batch Jobs
🪭2Launch batch images enhancements with HF Jobs
-
DALL·E mini via Hugging Face Jobs
🎨1DALL•E mini batch Jobs
-
Text2Any Batch with HF Jobs Orchestration
🧨3Launch and monitor Hugging Face inference jobs from a web UI
-
AudioLDM2 Batch with HF Jobs
🧨Launch and monitor audio generation jobs
-
Attention Is All You Need
Paper • 1706.03762 • Published • 122 -
Attention Residuals
Paper • 2603.15031 • Published • 185 -
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 80 -
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Paper • 2603.15557 • Published • 29
Research demos rebuilt for clarity, exploration, and better understanding of AI models.
Progressive list of MCP server ready trending spaces maintained by fffiloni
To-do: switch to HF Kernels
-
Kolors IP-Adapter
🖼160Create images from text and reference photos
-
InstantStyle
👁454Style-Preserving Text-to-Image Generation
-
Flux IP Adapter
🖼170Prompt with Images in flux[dev]
-
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Paper • 2411.15466 • Published • 39
All the steps to train your own SD-XL custom model
A collection full of musical tasks demos, for musicians & music enthusiasts
A collection of all papers referenced in OpenAI's "Video generation models as world simulators" technical report • openai.com/sora
An ongoing collection of games you can play on HF Spaces
How Text-to-Image evolved on HF and inspired the Community
All spaces made to convert a video (of GIFs) to anything useful in your pipelines
Demos I published that had significant impact, in order of publication
How ControlNet grew and shined on HF
All my demos involving music
All my demos involving video in or out
No crazy stuff, but useful ones for in-between steps
Everything you need to reproduce my Music-to-Image demo