Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 2 hours ago

hugging-apps/nemotron-3-5-transcribe

multimodalart updated a Space about 2 hours ago

hugging-apps/nemotron-3-5-transcribe

multimodalart published a Space about 2 hours ago

hugging-apps/auroraimg2-50m-preview

View all activity

hugging-apps 's Spaces 752

Nemotron 3.5 Transcribe

Multilingual ASR, translation & audio Q&A (40 langs)

AuroraIMG2-50M-Preview

50M-param from-scratch text-to-image model, 256x256

Anima Role Ref KV

Anima Role Ref KV - reference-guided character illustration

Anima Role Ref KV

One reference image + prompt → same character, new scene

Matcha Molecular Docking

Protein-ligand docking with Matcha flow matching

GenSfM

Uncalibrated multi-view images to 3D object and cameras

VGGT-Omega

Feed-forward 3D reconstruction from images or video

Voice Isolator — The Voice on the Line

Isolate the caller's voice from a call recording, streaming

Hi-Token Visual Grounding

Locate any region in an image from a text description

OBB-PBD

Oriented box grounding for aerial referring expressions

LFM3-VL-2B-VLD multipass

Browser-screenshot fixed-choice decisions from a 2B VLM

LFM3-VL-2B-VLD

Browser-screenshot decision model (VL-D protocol)

NLD-Uni

NVIDIA unified model - text-to-image, edit, VQA

MikołajRej — historical Polish handwriting OCR

OCR for historical Polish & Latin handwriting (Kraken E26)

LFM3-Audio-2B

Voice chat, ASR, translation & TTS with LFM3-Audio-2B

Ivme-Denoise-v1

2.97M-param blind image denoiser (Bayesian shrinkage U-Net)

d1-Omni-2B

One-pass typed decisions over audio, images and text

ZwZ2-27B

Visual question answering with multi-region reasoning

ZwZ2-4B

Multi-region visual reasoning VLM (Qwen3.5-4B, RL-trained)

LFM3-Omni-2B

Any-to-any: text/image/video/audio in, text or speech out

LFM3-VL-2B

LiquidAI vision-language model for images and video

MiniCPM-OCR 1.0

Document image OCR — text, tables, formulas, seals, charts

LOCUS-2B Visual Grounding

Ground referring expressions with draft-and-verify boxes

oruk-loop-153M

English ASR with a looped transformer (153M params)