Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 5 hours ago

hugging-apps/koharu-layout

multimodalart updated a Space about 5 hours ago

hugging-apps/koharu-layout

multimodalart published a Space about 9 hours ago

hugging-apps/typhoon-ocr2-0-8b

View all activity

hugging-apps 's Spaces 842

BluePixel-Turbo

Native 4K instruction-based image editing in 4 steps

Koharu Manga Layout Detection

Manga page layout segmentation with RF-DETR at 1920x1920

Typhoon OCR V2 0.8B

Thai/English document OCR with Typhoon OCR V2 0.8B

Typhoon OCR V2 2B

Thai/English OCR and document parsing with Typhoon OCR V2 2B

Video-Coder

Agent writes Blender code to build a 3D draft video

Klein-TTS X1.5 Pro

13M-param TTS in English, Spanish, French and Italian

Mithi v1 Flash

Text-to-speech for 11 Indian languages, two voices

Solv3R

Multi-view 3D reconstruction with a looped solver

OmniVoice Azerbaijani TTS

Azerbaijani text-to-speech with voice cloning

MOSS-Transcribe-Diarize

Speech transcription with diarization and timestamps

Bayan Arabic TTS

Arabic TTS with the fine-tuned Bayan "Murad" voice

VoiceTut Egyptian-Arabic TTS (diacritized)

Egyptian-Arabic diacritized text-to-speech

FLUX.2-klein-base-9B TailSteer

Drift-resistant multi-turn image editing, FLUX.2 Klein 9B

GLiDE-2B Decision Model

Typed questions in, calibrated probabilities out

Mirage · On-device structured vision

22 MB vision model - description, boxes, masks, OCR, forms

Underdog Woof

Two-voice English TTS that runs on CPU with numpy only

JDI-Decision-V1

Typed decisions with probabilities from JD's JDI-Decision-V1

GLiDE-9B

Typed decisions with calibrated probabilities

GLiDE-0.8B Decision Model

Typed questions in, calibrated probabilities out

VTR-2B Visual Token Routing

Computer-use VLM that routes vision tokens before acting

Agent-GenPath

Pathology patch synthesis with the Agent-GenPath DiT

GaussianRenderFormer

Transformer-based rendering of 3D Gaussian splats

VQ-SAM

Visual query segmentation — segment an object across video

Klang Pianissimo — Danish Speech to Text

Danish ASR with Klang Pianissimo, word timestamps