hysts's picture

hysts

hysts

gradio

·

AI & ML interests

Computer Vision

Recent Activity

liked a Space about 10 hours ago

YUXU915/TAG-MoE

new activity about 10 hours ago

YUXU915/TAG-MoE:Apply for a GPU community grant: Academic project

liked a Space 1 day ago

multimodalart/LLaDA-2-1

View all activity

Organizations

liked a Space about 10 hours ago

TAG-MoE

Task-Aware Gating for Unified Generative Mixture-of-Experts

liked 2 Spaces 1 day ago

LLaDA 2.1

Large Language Diffusion Models

VOID

VOID: Video Object and Interaction Deletion

liked 4 Spaces 2 days ago

Gemma 4 31B It

Chat with AI using text, images, or video

Gemma 4 26B-A4B It

Chat with an AI using text, images, or video

Gemma 4 E4B It

Chat with a multimodal AI about text, images, audio, video

Gemma 4 WebGPU

Run Gemma 4 locally in-browser on WebGPU w/ Transformers.js

liked a Space 5 days ago

LongCat AudioDiT 3.5B

Generate speech from text or clone a voice using a sample

liked a Space 7 days ago

MegaFlow Demo

Official demo for MegaFlow

liked 4 Spaces 9 days ago

PixelSmile Demo

PixelSmile Demo [🔨Developing]

Voxtral TTS Demo

Generate realistic speech from text with custom or preset voices

AutoGaze

Generate gaze pattern and reconstruction videos from any video

NVILA HD Video + AutoGaze

Long video understanding with smart attention

liked a Space 10 days ago

DetailGen3D

Generate detailed 3D model from image and coarse mesh

liked 3 Spaces 12 days ago

NV-Reason-CXR-3B Demo

Analyze chest X-rays and answer your medical questions

Qianfan-OCR Demo

Extract and process text from images with custom prompts

Kimodo

Generate high-quality motions from text prompts

liked a Space 15 days ago

Map Anything (v1)

Universal Feed-Forward Metric 3D Reconstruction

liked 2 Spaces 17 days ago

Foundation 1

Generate custom music clips from text prompts

DLSS 5 Anything

Turn any image into a DLSS 5 meme (using FLUX.2-klein-9b-kv)