Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 2 hours ago

hugging-apps/transvlm-shot-transitions

multimodalart updated a Space about 3 hours ago

hugging-apps/transvlm-shot-transitions

multimodalart published a Space about 3 hours ago

hugging-apps/irodori-tts-anime-demo

View all activity

hugging-apps 's Spaces 354

TransVLM Shot Transition Detection

Detect hard cuts and gradual shot transitions in video

Irodori-TTS v4.1 Anime

Anime-style Japanese TTS with voice cloning

EraseSAE

Surgical concept erasure in CogVideoX-5b video diffusion

ProgResViT

Adaptive-compute ViT that classifies in progressive rounds

ReCoSplat

Feed-forward 3D Gaussian Splatting from unposed video

DiMOO-Shortcut

Accelerated masked image generation with Lumina-DiMOO

VIBE — Video + Instruction → Background Music

Generate instruction-aligned background music for any video

PhenoSeq

Cell Painting images to single-cell transcriptomes

LULA-1.1 Protein-Ligand Binding Scorer

Sequence-only protein-ligand binding scorer (LULA-1.1)

Progression as Latent Drift

Forecast a future brain MRI from a baseline scan

EOVSAM Open-Vocabulary Segmentation

Segment any category you can name, in a single pass

AURA ULF Brain Segmentation

Segment 11 brain structures in ultra-low-field MRI

KorvaTTS

Vietnamese-first on-device TTS with code-switching

Puffin-World

Camera-controlled 3D world generation from one image

Temporal Context Routing

Script-timed multi-shot video with synced audio

LLaDA-Image-Turbo

4-step image generation and editing with LLaDA-Image

kraken PP-OCRv6 medium

Multilingual OCR/HTR for historical documents

DreamX-Creator 1.0

Image + prompt to video with jointly generated audio

TinyImageGen 0.6M

Unconditional 32x32 image sampling with a 0.6M-param model

StreamTalk

Speech to streaming 3D co-speech gesture animation

Qwen-Drive-1.0-4B

Driving VQA and motion planning with Qwen-Drive-1.0

Hojo ASR Multi V1

Multilingual speech recognition with Hojo-ASR-Multi-V1

VDN-H3

8-step hybrid-attention video + soundtrack, MiniMax-H3

AQ3D 3D Instance Segmentation

Segment indoor 3D scans into object instances