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: · 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 290 / 417
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
4/2-step text- & image-to-video+audio, PDMD on MiniMax-H3
Upstream model links: MiniMaxAI/MiniMax-H3 · pdmd2026/pdmd_4NFE_lora · pdmd2026/pdmd_2NFE_lora
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
155M-parameter MMDiT text-to-image model
Upstream model links: bench-labs/PixelModel-v6 · google/flan-t5-base · madebyollin/sdxl-vae-fp16-fix · openai/clip-vit-base-patch32
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Scientific multimodal model for RNA/DNA/protein/molecules
Upstream model links: facebook/esm2_t33_650M_UR50D · facebook/sam3 · Qwen/Qwen3-VL-4B-Instruct · sais-org/Polaris_Pro
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Driving VQA and motion planning with Qwen-Drive-1.0
Upstream model links: Qwen/Qwen-Drive-1.0-4B
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Canny/depth/pose/… control + inpainting for Qwen-Image 2.1
Upstream model links: alibaba-pai/Qwen-Image-2.1-Fun-Controlnet-Union · Qwen/Qwen-Image-2.1
Declared repository license: other
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Unified TTS, singing, and mixed speech+song generation
Upstream model links: ASLP-lab/SemBridge
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Multi-modal omni-task vision model demo
Upstream model links: google/siglip-base-patch16-224 · OpenGVLab/InternVL · Qwen/Qwen-tokenizer · Qwen/Qwen2-7B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Unified text-to-image generation and image understanding
Upstream model links: Qwen/Qwen3-0.6B · tencent/Rosetta-inference · google-bert/bert-base-cased · google-bert/bert-base-uncased
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Omni-modal image, audio and video understanding
Upstream model links: TaoLiveAIGC/TLive-Omni-4B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Next desktop GUI action from a screenshot + instruction
Upstream model links: tencent/UI-Mate-27B · Salesforce/ctrl
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
GUI grounding — locate UI elements from screenshots
Upstream model links: inclusionAI/UI-Venus-2-9B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Generate radiology reports from chest X-ray images
Upstream model links: microsoft/UniRG-CXR
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Zero-shot voice cloning with the UniVoice ASR+TTS LLM
Upstream model links: guanwenhao/univoice-all · HuggingFaceTB/SmolLM2-360M · nvidia/bigvgan_22khz_80band · openai/whisper-large-v3-turbo
Declared repository license: mit
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Watch & think simultaneously — streaming video reasoning
Upstream model links: Catalan258/VST-7B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Streaming Arabic speech-to-text (MSA + dialects)
Upstream model links: mistralai/Voxtral-Mini-4B-Realtime-Arabic
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Cognitive reasoning web agent over webpage screenshots
Upstream model links: Gnonymous/Web-CogReasoner
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Turn document page images into structured Markdown
Upstream model links: tencent/WeVisDoc · tencent/WeVisDoc-4B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Spatial & visual reasoning VLM — images and video
Upstream model links: TaichuAI/ZDTaichu5.0-9B
Community record · not individually tested
Publisher: huggingface-projects
Upstream model links: mishig/llms-txt · google-t5/t5-small
Declared repository license: mit
Community record · not individually tested
Publisher: husseinelsaadi
Publisher summary (original)
Real photo or AI-generated? 1100+ generators, calibrated
Upstream model links: openai/clip-vit-base-patch16
Declared repository license: cc-by-nc-4.0
Community record · not individually tested
Publisher: hxari
Upstream model links: 4deffo/tamil-ner · tamilnlpSLIIT/varta-t5-grammar-check
Community record · not individually tested
Publisher: hy3dlab
Publisher summary (original)
Revision-pinned general and LoRA AI image editor
Upstream model links: autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime · dx8152/Qwen-Edit-2509-Light-Migration · dx8152/Qwen-Edit-2509-Multiple-angles · fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: i1o1n1e1
Publisher summary (original)
Generate uncensored images and videos with AI models
Upstream model links: John6666/bond-nsfw-v50-sdxl · John6666/lustify-sdxl-nsfwsfw-v2-sdxl · John6666/spicy-realism-nsfw-mix-v30-sdxl · John6666/wai-nsfw-illustrious-v80-sdxl
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: iMeshal
Publisher summary (original)
Persistent Chat: A Summarization-Based AI Dialogue System
Upstream model links: facebook/bart-large-cnn · meta-llama/Llama-2-7b-chat-hf
Declared repository license: llama2