Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 1 hour ago

hugging-apps/abot-recon-streaming-3d

multimodalart updated a Space about 1 hour ago

hugging-apps/abot-recon-streaming-3d

multimodalart published a Space about 2 hours ago

hugging-apps/code-as-world-vl-demo

View all activity

hugging-apps 's Spaces 320

Hviske v5.3 Danish ASR

Danish speech-to-text with hviske-v5.3 Conformer model

GestureLSM

Latent Shortcut based Co-Speech Gesture Generation

Marionette

Play a game world model live - steer it frame by frame

SIFT-VTON

Virtual try-on with SIFT correspondence supervision

Trendyol-Vision-Master

E-commerce catalog VLM for Turkish product listings

Alaya-EVOKE Text-to-Video

Text-to-video world model (Evoke, 14B DiT, 3-step distilled)

Bernini Diffusers v2

Reference-to-video with ByteDance Bernini-Diffusers-v2

UA-NWM Aerial Navigation

Uncertainty-aware world model for aerial navigation

JoyAI Video Edit

Streaming instruction-guided video editing

MiniWorld Simulator

Drive a video world model with a camera path from one frame

Light Forcing Video Generation

Text-to-video with Light Forcing sparse attention

Orca-4B World Model

World-state visual QA with BAAI Orca-4B

Rosetta Multimodal

Unified text-to-image generation and image understanding

Texture to Albedo

Extract flat albedo maps from textures with FLUX.2 Klein

SenseNova-Vision-7B-MoT

Multi-modal omni-task vision model demo

Giga-World-1 Controllable I2V

Controllable image-to-video with Giga-World-1

Krea 2 Ostris Edit

Reference-image conditioned generation with Krea 2

IRG-MotionLLM Text-to-Motion

Text-to-3D human motion generation

NABLA Wan2.1 T2V

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

InternVLA-A1.5 VLA Action Explorer

Predict robot action chunks from an image + instruction

Ex-Omni Talking Avatar

Text/speech to spoken response + 3D talking-avatar video

MMDiff

Multi-modal generation with diffusion transformers

RefControl FLUX.2 Klein - Reference + Lineart

Keep identity from reference, follow lineart structure

MAOAM

Object and Material Selection VLM