Hugging Apps

community

AI & ML interests

None defined yet.

Recent Activity

multimodalart published a Space about 4 hours ago

hugging-apps/unispace-gen-edit

multimodalart updated a Space about 6 hours ago

hugging-apps/unispace-gen-edit

multimodalart published a Space about 7 hours ago

hugging-apps/minimax-h3-controlnet-union

View all activity

hugging-apps 's Spaces 292

UniSpace

Unified text-to-image generation and instruction editing

MiniMax H3 Fun ControlNet Union

Control-video + prompt to video with sound, MiniMax-H3

Next Forcing World Model

Causal world model for robot video generation

TLive-Omni-4B

Omni-modal image, audio and video understanding

FastH3 Preview

4-step MiniMax-H3 — video with a matching soundtrack

Anima 3.8B

Anime text-to-image with a Qwen3.5 4B cross-adapter

Kodama JA Streaming ASR

Japanese streaming ASR fine-tuned on 35k hours of speech

TinyCast Forecaster

TinyCast zero-shot probabilistic time-series forecasting

PRISM Text-to-Motion

Generate human motion sequences from text prompts

4DAnyone Multi-View Video

Monocular portrait video to multi-view videos

SenseNova-U1.5-8B-MoT

Unified text-to-image and image editing model

ORV Robot Video Generation

Action-conditioned robot manipulation video generation

Molmo2Fish Tracking

Track fish in sonar video, fix it with plain English

OmniAlign

Multilingual word and sentence alignment

FiSeR AI Image Detector

Detect AI-generated images with FiSeR DINOv3 ViT-L/16

MR-IQA-2 Image Quality Assessment

Blind image quality assessment with faithful reasoning

SA-IQA Spatial Aesthetics

Assess spatial aesthetics of interior images

SenseNova-U1.5-8B-MoT-SFT

Unified text-to-image and image editing (SFT checkpoint)

Krea 2 Turbo 4-Step Distillation LoRA

Krea 2 Turbo in 4 steps via distillation LoRA

MiniMax-H3 Turbo-SLA

4-step distilled image-to-video with SLA sparse attention

StreamOPD Streaming Video QA

Streaming video QA from the 4 most recent frames

CN-MultiDialect-ASR Demo

Chinese dialect ASR for Mandarin, Cantonese, Wu & more

Qwen-Video-Edit

Instruction-based video editing with Qwen-Image-Edit

MathForm-8B Autoformalization

Turn natural-language math into Lean 4 statements