Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart updated a Space 13 minutes ago

hugging-apps/bina-koochik-persian-ocr

multimodalart published a Space 13 minutes ago

hugging-apps/bina-koochik-persian-ocr

multimodalart updated a Space about 14 hours ago

hugging-apps/mage-vl-demo

View all activity

hugging-apps 's Spaces 158

Bina 0.1 Koochik Persian OCR

Persian OCR with Bina 0.1 Koochik VLM

Mage-VL

Codec-native video & image understanding with Mage-VL 4B

CrisperWhisper 2.0 Controllable ASR

Controllable verbatim/intended ASR with word-level timing

ShotPlan Cinematic T2V

Multi-shot cinematic text-to-video generation

LongE2V Event-Video Reconstruction

Reconstruct video from event-camera voxel grids via LongE2V

ScenA Audio Scene Generation

Reference-driven multi-speaker audio scene generation

GLiNER Streaming PII Detector

Zero-shot PII detection with GLiNER streaming-span model

Fara1.5-4B Web Computer-Use Agent

Live multi-step Fara browser-agent loop on real websites

UniSE Speech Enhancement

Unified AR-LM-based speech enhancement & separation

WordVoice Word-Level Controllable TTS

Zero-shot TTS with explicit word-level prosody control

PepperOCR-1-4B Demo

Multilingual document image to Markdown OCR

Cosmos3-Super Image-to-Video (4-Step)

Animate a first frame with Cosmos3-Super I2V (64B, 4-step)

Fara-1.5-27B Computer-Use Agent

Web computer-use agent — screenshot + task to next action

RynnBrain 1.1-2B Demo

Embodied AI VLM for visual grounding and planning

Lung Ultrasound Video Classification

4-class lung ultrasound video classifier with attention

Mage-Flow-Base

Text-to-image with Microsoft Mage-Flow-Base (4.1B MMDiT)

Bina 0.1 Persian OCR

Persian OCR with Bina 0.1 vision-language model

GeoChrono

Temporal reasoning over multi-temporal satellite imagery

VEGA-3D Spatial Reasoning

3D spatial reasoning VLM with video-diffusion 3D priors

Orbis 2 World Model

Hierarchical driving world model — predict future frames

Video Streaming Thinking (VST-7B)

Watch & think simultaneously — streaming video reasoning

LingBot-Video Dense 1.3B

Dense 1.3B embodied video generation — T2V, I2V, T2I

Cosmos3-Edge Physical AI Reasoning

NVIDIA Cosmos3-Edge — reason over images & video

TimeLens2-2B

Video temporal grounding with TimeLens2-2B