Hugging Apps

Team

community

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 7 hours ago

hugging-apps/silencio-tts

multimodalart updated a Space about 7 hours ago

hugging-apps/silencio-tts

multimodalart published a Space about 21 hours ago

hugging-apps/licon-live-talk

View all activity

hugging-apps 's Spaces 721

WebBrain VL 2 450M

🖥

Browser-GUI screenshot to structured observation text

Korean PII Detector

🔍

Detect PII in Korean text with a 34M param model

RUM-FLUX.2-klein-4B

🎨

Anime image generation & editing via distillation

UI-Venus-2-9B GUI Grounding

🎯

GUI grounding — locate UI elements from screenshots

Zing 0.5 AoTI Compiler

⚙

torch.export + AOTInductor compiler for Zing-0.5

GigaBrain-0.7 VLA

🦾

Predict robot action chunks with GigaBrain-0.7 3.5B

136

MiniMax-H3 4-Step FlashGen LoRA

⚡

4-step text-to-video+audio with MiniMax-H3 FlashGen LoRA

OneHOI Human-Object Interaction Editing

🎯

Edit human-object interactions in images with OneHOI.

BenthicFlow

🪸

Generate extensible underwater 3D scenes with flow matching

AdaSemSeg Few-Shot Seismic Facies Segmentation

🌊

Few-shot seismic facies segmentation via GP regression

Granite Speech 5.0 TurboCTC ASR

🎤

Fast English ASR with IBM Granite Speech TurboCTC

Loopy

🔁

Seamless looping video generation with Wan2.2 + Loopy

Canter T2I Demo

🎨

Canter 2B text-to-image flow model

GLiNER2.5 Small — Information Extraction

🔎

Zero-shot entities, classes, relations & JSON records

GLiNER2.5 Multi — Zero-Shot Information Extraction

🔍

Zero-shot entity, classification, relation extraction

135

SenseNova-U1.5-8B-MoT

🎨

Unified text-to-image and image editing model

GLiNER2.5-base Information Extraction

🔍

Schema-driven NER, classification & relation extraction

UniSpace

🛰

Unified text-to-image generation and instruction editing

MiniMax H3 Fun ControlNet Union

🎬

Control-video + prompt to video with sound, MiniMax-H3

Next Forcing World Model

🎬

Causal world model for robot video generation

TLive-Omni-4B

📡

Omni-modal image, audio and video understanding

FastH3 Preview

🎬

4-step MiniMax-H3 — video with a matching soundtrack

Anima 3.8B

🦊

Anime text-to-image with a Qwen3.5 4B cross-adapter

Kodama JA Streaming ASR

🎙

Japanese streaming ASR fine-tuned on 35k hours of speech