Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 2 hours ago

hugging-apps/mr-pong-rl-demo

multimodalart updated a Space about 2 hours ago

hugging-apps/mr-pong-rl-demo

multimodalart published a Space about 3 hours ago

hugging-apps/navidc-ocr-demo

View all activity

hugging-apps 's Spaces 259

SupraCMA-8M

SupraCMA-8M Channel-Mixing Attention language model

Kairos World Action Model

Kairos 4B world-action model for robot video generation

OvisOCR2 Document to Markdown

Parse document images into Markdown with OvisOCR2

SwiftVR

Real-time one-step generative video restoration

LTX-2.3 Cinemagraph (Fast / fp8)

Fast fp8 still-to-cinemagraph (LTX-2.3-22B LoRA)

3D HAMSTER — 3D Trajectory Prediction

Predict metric 3D robot trajectories from RGB-D + language

MirrorPPR

Exemplar-based portrait photo retouching

LTX-2.3 Cinemagraph

Still image to looping cinemagraph (LTX-2.3-22B LoRA)

Polaris-Pro Scientific Multimodal Model

Scientific multimodal model for RNA/DNA/protein/molecules

RynnWorld-4D

4D world model — synced RGB, depth & optical-flow video

UniICL

Unified multimodal in-context learning demo

Krea 2 Ostris Edit

Reference-image conditioned generation with Krea 2

ToolMerge Video Keyframe Retrieval

Decompose queries into tool calls for keyframe retrieval

MiniBananaMind-v4-9M

Tiny 8.9M param text generation demo

Ettin Reranker 68M

Rerank passages by relevance with a 68M cross-encoder

Omni-Diffusion

Any-to-any multimodal masked discrete diffusion model

Geometric Reciprocity Stereo Video

Convert 2D videos into stereoscopic 3D with GRT

FLUX.1-dev CMO Compositional

FLUX.1-dev fine-tuned with CMO for compositional generation

GeoWorld

Generate 3D scene videos from a single image

NABLA Wan2.1 T2V

NABLA-accelerated Wan2.1 text-to-video generation

Web-CogReasoner

Cognitive reasoning web agent over webpage screenshots

Pixels Points Polygons Building Vectorizer

Extract building polygons from aerial images (P3 / Pix2Poly)

IRG-MotionLLM Text-to-Motion

Text-to-3D human motion generation

Light-Omni Video Understanding

Agentic video understanding with reflex-style reasoning