Community AI applications

Explore community AI applications and interactive demos beyond the product directory. Find candidates by purpose, then check the publisher's page for usage requirements.

Records come from public Hugging Face metadata with automated screening and deduplication. They are not individually tested or a count of distinct commercial products. Apps may sleep, require keys, paid compute or sign-in; their status may have changed.

Snapshot: 2026-10-15 UTC · Source: Hugging Face Spaces

Categories are matched automatically from metadata. Names, summaries, model links and licenses are publisher supplied; repository licenses may not cover associated models or commercial use.

10,000 matching apps · Page 19 / 417

Community record · not individually tested

HunyuanImage-3.0 ↗

Publisher: akhaliq

Images and visionSnapshot status: Running

Upstream model links: tencent/HunyuanImage-3.0

HF likes: 182View application and source ↗

Community record · not individually tested

Distill Any Depth ↗

Publisher: xingyang1

Other / not yet classifiedSnapshot status: Running

Upstream model links: xingyang1/Distill-Any-Depth

Declared repository license: apache-2.0

HF likes: 182View application and source ↗

Community record · not individually tested

Cube3d Interactive ↗

Publisher: Roblox

Publisher summary (original)

interactive demo for cube 3d model

3D and spatialSnapshot status: Running

Upstream model links: openai/shap-e · Roblox/cube3d-v0.5 · Roblox/cube3d-v0.1

Declared repository license: openrail

HF likes: 181View application and source ↗

Community record · not individually tested

Whisper Speech X DreamTalk ↗

Publisher: fffiloni

Publisher summary (original)

Combine voice cloning and portrait lipsync animation

Video and animationSnapshot status: Running

HF likes: 180View application and source ↗

Community record · not individually tested

MarioGPT ↗

Publisher: multimodalart

Text and languageSnapshot status: Running

Upstream model links: facebook/bart-base · shyamsn97/Mario-GPT2-700-context-length · distilbert/distilgpt2

Declared repository license: mit

HF likes: 180View application and source ↗

Community record · not individually tested

Ovis2.5 9B ↗

Publisher: ATH-MaaS

Publisher summary (original)

High-accuracy vision & reasoning for complex tasks

Images and visionSnapshot status: Running

Upstream model links: ATH-MaaS/Ovis2.5-9B

Declared repository license: apache-2.0

HF likes: 179View application and source ↗

Community record · not individually tested

Image2SFX Comparison ↗

Publisher: fffiloni

Publisher summary (original)

Generates audio environment from an image

Audio and speechSnapshot status: Running

Upstream model links: declare-lab/tango2 · facebook/audio-magnet-medium · facebook/audio-magnet-small · facebook/magnet-medium-10secs

HF likes: 179View application and source ↗

Community record · not individually tested

Baby Reachy-Mini Companion ↗

Publisher: ravediamond

Publisher summary (original)

A fully local Reachy Mini AI Companion for babies and kids.

Other / not yet classifiedSnapshot status: Running

Upstream model links: hexgrad/Kokoro-82M · jafet21/yamnetonnx

HF likes: 179View application and source ↗

Community record · not individually tested

Carbon ↗

Publisher: HuggingFaceBio

Other / not yet classifiedSnapshot status: Running

Upstream model links: HuggingFaceBio/Carbon-3B · HuggingFaceBio/Carbon-500M · HuggingFaceBio/Carbon-8B

HF likes: 178View application and source ↗

Community record · not individually tested

GLiNER-medium-v2.1, zero-shot NER ↗

Publisher: tomaarsen

Other / not yet classifiedSnapshot status: Running

Upstream model links: urchade/gliner_base · urchade/gliner_medium-v2.1

Declared repository license: apache-2.0

HF likes: 178View application and source ↗

Community record · not individually tested

Gemma Avatar ↗

Publisher: victor

Publisher summary (original)

Talk to Gemma 4 face to face, with a 3D lip-synced avatar

3D and spatialSnapshot status: Running

Upstream model links: google/gemma-4-31B-it · nvidia/parakeet-tdt-1.1b · Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

HF likes: 178View application and source ↗

Community record · not individually tested

VibeVoice ↗

Publisher: yasserrmd

Audio and speechSnapshot status: Running

Upstream model links: aoi-ot/VibeVoice-7B · aoi-ot/VibeVoice-Large · microsoft/VibeVoice-1.5B · microsoft/VibeVoice-Large

HF likes: 178View application and source ↗

Community record · not individually tested

Zeroscope V2 ↗

Publisher: hysts

Publisher summary (original)

text-to-video

Video and animationSnapshot status: Running

Upstream model links: cerspense/zeroscope_v2_576w

Declared repository license: mit

HF likes: 177View application and source ↗

Community record · not individually tested

LTX 2.3 Sync ↗

Publisher: linoyts

Publisher summary (original)

Portrait animation & lipsync with LTX 2.3

Video and animationSnapshot status: Running

Upstream model links: google/gemma-3-12b-it-qat-q4_0-unquantized · HuggingFaceTB/SmolVLM2-500M-Video-Instruct · Lightricks/LTX-2.3 · Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control

HF likes: 177View application and source ↗

Community record · not individually tested

Lp Music Caps ↗

Publisher: seungheondoh

Audio and speechSnapshot status: Running

Upstream model links: facebook/bart-base · seungheondoh/lp-music-caps

Declared repository license: mit

HF likes: 177View application and source ↗

Community record · not individually tested

AudioX ↗

Publisher: Zeyue7

Audio and speechSnapshot status: Running

Upstream model links: archinetai/audio-diffusion-pytorch · facebook/encodec_32khz · google/flan-t5-base · google/flan-t5-large

Declared repository license: cc-by-nc-4.0

HF likes: 176View application and source ↗

Community record · not individually tested

PitchFight AI ↗

Publisher: build-small-hackathon

Publisher summary (original)

An AI founder pressure arena for practicing startup pitches.

Other / not yet classifiedSnapshot status: Running

Declared repository license: mit

HF likes: 176View application and source ↗

Community record · not individually tested

StyleTTS2: Ukrainian text to speech ↗

Publisher: patriotyk

Publisher summary (original)

StyleTTS2 trained on Ukrainian multispeaker dataset

Audio and speechSnapshot status: Running

Upstream model links: patriotyk/styletts2_ukrainian_single · skypro1111/m2m100-ukr-verbalization · skypro1111/m2m100-ukr-verbalization-ct2 · patriotyk/styletts2_ukrainian_multispeaker_hifigan

Declared repository license: mit

HF likes: 175View application and source ↗

Community record · not individually tested