hysts

hysts

huggingface

·

AI & ML interests

Computer Vision

Recent Activity

liked a Space about 4 hours ago

fffiloni/SCAIL-2

updated a Space 5 days ago

huggingface-projects/gemma-4-12b-it

updated a Space 5 days ago

huggingface-projects/gemma-4-31b-it

View all activity

Organizations

liked a Space about 4 hours ago

SCAIL 2

Unifying Controlled Character Animation

liked a Space 6 days ago

MMEB Leaderboard

The massive multimodal embedding benchmark

liked 2 Spaces 9 days ago

Krea 2

Krea 2 text-to-image (Raw + Turbo)

Unlimited OCR

Extract text from images and PDFs instantly

liked a Space 11 days ago

MOSS-TTS Local Transformer v1.5

Multilingual 48kHz TTS with zero-shot voice cloning

liked a Space 13 days ago

Figurine Factory

Turn any photo into a collectible 3D figurine

liked a Space 17 days ago

PRX Pixel

Public test Space for pixel-space PRX t2i

liked a Space 20 days ago

Zonos 2

Zyphra's expressive multilingual TTS with voice cloning

liked 4 Spaces 22 days ago

DiffusionGemma vs Gemma-4 — Post-OCR Correction

Diffusion vs autoregressive LLM on historical OCR cleanup

Gemma Diffusion 3D Asset Builder

Diffuse an SVG game asset and watch it extrude into live 3D

FFASR Leaderboard

Far-Field ASR — clean / noisy / reverberant benchmark

Gemma Diffusion Website Builder

Watch a diffusion LLM write a website live, then tweak it

liked 2 Spaces 23 days ago

Miso TTS 8B

8B CSM-style text-to-speech with voice cloning

Monuments de Paris

Explore interactive 3D models of Paris monuments

liked 2 Spaces 25 days ago

Nemotron 3.5 ASR Streaming

Multilingual streaming ASR with NeMo

Dots.tts

Generate natural-sounding speech from typed text

liked a Space 28 days ago

Magenta RT Jam

Play notes to steer real-time music (PyTorch)

liked 3 Spaces 29 days ago

Ideogram 4

Ideogram 4 state of the art open weights

Follow the Mean (FLUX.2)

Training-free reference-guided generation with FLUX.2-klein

Cosmos3-Nano

NVIDIA Cosmos3-Nano — text/image to video + audio