hysts's picture

hysts

hysts

gradio

·

AI & ML interests

Computer Vision

Recent Activity

upvoted an article about 7 hours ago

State of Open Source on Hugging Face: Spring 2026

liked a Space 1 day ago

H-Liu1997/FloodDiffusion-Streaming

new activity 1 day ago

H-Liu1997/FloodDiffusion-Streaming:Apply for community grant: Academic project (gpu)

View all activity

Organizations

liked a Space 1 day ago

FloodDiffusion Streaming Demo

Streaming Motion Generation (CVPR 2026)

liked 2 Spaces 3 days ago

SegviGen

Segment 3D models into parts using optional 2D maps

LongStream Demo

Launch an interactive Gradio demo interface

liked a Space 4 days ago

Any2Full

Generate a dense depth map from an RGB image and sparse depth

liked a Space 5 days ago

DVD

Official demo of DVD (https://dvd-project.github.io/)

liked a Space 6 days ago

TADA — Text-Acoustic Dual Alignment for Speech

Speech generation from text and acoustic reference

liked 2 Spaces 7 days ago

Voxtral Realtime WebGPU

Real-time speech transcription, entirely in your browser.

TADA

Generate speech that mimics a given voice from text

liked a Space 8 days ago

Fish Audio S2 Pro

Zero GPU Text-to-Speech using Fish Audio S2 Pro

liked a Space 9 days ago

SoulX-Singer

Generate singing voice from lyrics or convert voices

liked 2 Spaces 12 days ago

LTX 2.3 Distilled

Generate cinematic videos from text prompts and images

Helios 14B RealTime

Generate videos from text, images, or video

liked a Space 13 days ago

GQIR

[CVPR 2026] Generative Quanta Image Reconstruction

liked 4 Spaces 14 days ago

Magic Fixup

Streamlining photo editing by watching dynamic videos

Text Behind Video

Create cinematic video designs locally in your browser

FireRed OCR

FireRed-OCR for Document Recognition

KittenTTS Demo

Generate spoken audio from typed text

liked a Space 15 days ago

OmniLottie

Official Demo Page of OmniLottie.

liked 2 Spaces 20 days ago

faster-qwen3-tts

Generate spoken audio from text with custom or cloned voices

Videomt Transformers Demo

Segment videos with instance, semantic, or panoptic masks