hysts

hysts

huggingface

·

AI & ML interests

Computer Vision

Recent Activity

published a Space about 1 hour ago

hysts-debug/gradio-13923-after

published a Space about 1 hour ago

hysts-debug/gradio-13923-before

updated a Space about 2 hours ago

hysts-debug/gradio-13923-after

View all activity

Organizations

liked a Space about 9 hours ago

World Models: The Simulation Strikes Back

The Simulation Strikes Back -- what even is a world model?

liked 2 Spaces 1 day ago

Audio8 ASR Infinite

Native streaming Chinese/English ASR, 80ms clock

Jev Decision Index

Benchmarks and news on various repros of TypeSafe's Jev

liked a Space 9 days ago

Qwen-Image-2.1

Generate and edit images with Qwen-Image-2.1

liked a Space 13 days ago

YuE2-3B Music Generator

Generate songs and covers from style prompts and lyrics.

liked a Space 14 days ago

AuK

Unified speech generation and editing with AuK

liked a Space 18 days ago

A Hitchhiker's Guide to the 3D Ecosystem

An interactive guide to 3D representations.

liked 2 Spaces 20 days ago

Marigold V2

Depth, surface normals, and albedo from a single image

Open TTS Leaderboard

Rate and compare TTS model speech samples

liked a Space 21 days ago

MiniCPM5 2B Demo

MiniCPM5-2B-Demo

liked 3 Spaces about 1 month ago

FireRedTTS3

Voice cloning, voice design and speech editing

Breeze TTS 2

Bilingual TTS with voice design, cloning, and direction

S1-mini Transcript Cleanup

Clean and normalize raw ASR transcripts with S1-mini

liked 7 Spaces about 2 months ago

MiniMax Music 3 Studio

Generate custom music tracks from text captions and lyrics

LTX-2.5

LTX-2.5 distilled two-stage

MiniMax-H3 Ultra Fast

Ultra-fast local NVFP4 video + synchronized audio generation

UniPASE Speech Enhancement

Universal speech enhancement with high fidelity

MiniMax H3

Video generation with a synchronized soundtrack

SymphonyGen Demo

Orchestral generation controlled by a harmony skeleton

QueenVIS Video Instance Segmentation

Segment and track object instances in video with QueenVIS