Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart updated a Space about 1 hour ago

hugging-apps/moss-tts-pny

multimodalart published a Space about 1 hour ago

hugging-apps/moss-tts-pny

multimodalart updated a Space about 3 hours ago

hugging-apps/sam2matting

View all activity

hugging-apps 's Spaces 71

SAM2Matting

Image matting with diverse prompts via SAM2Matting

MOSS-TTS-PNY

Speaker-conditioned TTS with emotion & energy control

MMDiff

Multi-modal generation with diffusion transformers

Anima ControlNet VACE Depth

Anima depth-conditioned image generation via VACE ControlNet

BS-Roformer Leap Audio Separator

Separate audio into vocals and instruments with BS-Roformer

DoctoBERT-fr-base

Fill-mask demo for French medical RoBERTa

WATERec WordArt Recognition

Recognize text from WordArt / artistic scene text images

Whisper Small Polish

Polish speech recognition with fine-tuned Whisper Small

Fast-FoundationStereo

Real-time zero-shot stereo disparity estimation

PhoneBuddy-4B

Phone-use GUI agent - screenshot + task to next action

Translate-15L

Compact 60M T5 translator for 15 languages

VideoSearch-R1

Video verification & temporal grounding with VideoSearch-R1

VISTA GUI Grounding

GUI grounding with VISTA-9B — predict click coordinates

ViT-Up Feature Upsampler

DINOv3 feature upsampling with ViT-Up

VIEW2SPACE-4B

Multi-view visual reasoning VLM based on Qwen3-VL 4B

RefControl FLUX.2 Klein - Reference + Lineart

Keep identity from reference, follow lineart structure

FlowUpscaler

2x latent super-resolution with FlowUpscaler in Flux.2 space

MAOAM

Object and Material Selection VLM

Qwen3 Forced Aligner

Word-level timestamp alignment from audio + transcript

JoyAI Image Edit Plus

Multi-image instruction-guided image editing

KDL-Frontier-Parser-nano

Document-parsing VLM (1.2B) by KoreaDeep

DomainShuttle Subject Video

Subject-driven text-to-video from reference images (Wan2.2)

Kokoro Vietnamese TTS

Vietnamese text-to-speech with Kokoro TTS

SenseNova-U1-8B-MoT-Interleaved

Interleaved text and image generation with SenseNova-U1