Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart updated a collection about 7 hours ago

Community Spaces

multimodalart updated a collection about 7 hours ago

Community Spaces

multimodalart updated a collection about 7 hours ago

Community Spaces

View all activity

hugging-apps 's Spaces 62

Structured Defect Grounding

Ground localized defects in AI-generated images

SwiftVR

Real-time one-step generative video restoration

MOSS-Transcribe-preview-2B

Speech-to-text transcription with MOSS-Transcribe-preview-2B

PhoneBuddy Agent

Phone-use GUI agent that predicts actions from screenshots

Krea 2 Enhancer

Enhance text-to-image with the Krea2 Enhancer LoRA on Turbo

IdeoKrea Style LoRA

Krea-2-Turbo with IdeoKrea style LoRA demo

Qwen3-ASR 0.6B

Multilingual speech recognition in 30+ languages

InternVideo3-8B-Instruct Demo

Video understanding with InternVideo3 M²LA multimodal LLM

LoomVideo

Unified multimodal video generation and editing (5B)

SauerkrautLM-LFM2.5-GLiNER

Zero-shot multilingual NER with GLiNER on LFM2.5-350M

SeFi-Image 5B Turbo

Semantic-First Diffusion text-to-image in 4 steps

PP-OCRv6 Medium Text Recognition

PP-OCRv6 medium recognition — text recognition from images

PP-OCRv6 Medium Text Detection

Detect text regions in images with PP-OCRv6 medium

DIRECT 3D-Aware Object Insertion

3D-aware object insertion with the DIRECT model (ICML 2026)

BioMatrix-4B-SFT

Multimodal bio foundation model for molecules & proteins

Qwen3-ASR-1.7B

ASR for 52 languages and dialects

Echo-Infinity

Infinite video generation with learnable evolving memory

LTX-2.3 Foley LoRA

Add Foley sound effects to silent videos with LTX-2.3

Slack Actions

Slack interactivity endpoint for the HuggingDemos queue

TRIAGE Clinical Risk Predictor

Dialectical reasoning for ICU mortality risk prediction

Echo-Memory Action World Model

Action-conditioned video world model demo

Supra-A2A-Nano-Exp

Tiny any-to-any multimodal GPT (text + image) prototype demo

DI2FIX Enhancer

Distractor-free 2D enhancer for radiance field renderings

JoyAI-VL-Interaction-Preview

Vision-driven VLM for image and video understanding