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 210 / 417
Community record · not individually tested
Publisher: hfmlsoc
Publisher summary (original)
Uses HF inference and academic APIs for directed lit review
Upstream model links: google/gemma-4-26B-A4B-it · HuggingFaceTB/SmolLM3-3B · ibm-granite/granite-embedding-english-r2 · MiniMaxAI/MiniMax-M2
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: himanshukumar378
Publisher summary (original)
Multiple PDF Chatbot is an AI-powered tool that allows users
Upstream model links: google/flan-t5-base · sentence-transformers/all-MiniLM-L6-v2
Declared repository license: mit
Community record · not individually tested
Publisher: hksung
Upstream model links: hksung/ASC_tagger_v2
Community record · not individually tested
Publisher: hongst
Upstream model links: nlpai-lab/MixLID
Community record · not individually tested
Publisher: horiyouta
Upstream model links: hfl/chinese-roberta-wwm-ext-large · ku-nlp/deberta-v2-large-japanese-char-wwm · litagin/sbv2_amitaro · litagin/sbv2_koharune_ami
Community record · not individually tested
Publisher: hotchpotch
Upstream model links: hotchpotch/japanese-splade-v2
Declared repository license: mit
Community record · not individually tested
Publisher: huchenchat
Upstream model links: Shakker-Labs/SD3.5-LoRA-Chinese-Line-Art
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Multimodal typed decisions with probabilities from Clef-Omni
Upstream model links: Cloudflare/clef-omni
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
One-pass calibrated decisions from an image
Upstream model links: Mapika/decider-2b-vision
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Global field boundary delineation from satellite imagery
Upstream model links: MykolaL/DelineateAnything
Declared repository license: agpl-3.0
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
One-step 1080p refinement of MiniMax-H3 videos
Upstream model links: Efficient-Large-Model/SoL-Refiner-LTX-2.5-for-MiniMax-H3 · diffusers-internal-dev/minimax-h3-sol-kernels
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
8-step MiniMax-H3 — video with a matching soundtrack
Upstream model links: FastVideo/FastVideo-FastH3-8-Step-V2 · MiniMaxAI/MiniMax-H3 · multimodalart/MiniMax-H3
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
2x latent super-resolution with FlowUpscaler in Flux.2 space
Upstream model links: black-forest-labs/FLUX.2-klein-4B · TensorForger/FlowUpscaler
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Gestalt unified multimodal discrete diffusion, text-to-image
Upstream model links: GeWu-Lab/Gestalt · TencentARC/IBQ-Tokenizer-16384
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Multilingual speech recognition (RU, EN, KK, KY, UZ)
Upstream model links: ai-sage/GigaAM-Multilingual
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
One checkpoint, any label set, instant text decisions
Upstream model links: fastino/GLiNER2.5-Decide
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
4-step MeanFlow Japanese TTS with voice cloning
Upstream model links: Aratako/Irodori-TTS-v4.1-Small-MF · Aratako/Irodori-TTS-v4.1-Small · Aratako/Semantic-DACVAE-Japanese-32dim
Declared repository license: mit
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Calibrated typed decisions on text + images, one pass
Upstream model links: autotrust/JEV-27B · autotrust/JEV-27B-VL
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
FPS-controlled image-to-video with Kandinsky 5.0
Upstream model links: kandinskylab/Time-Adapter · kandinskylab/Kandinsky-5.0-I2V-Lite-5s
Declared repository license: mit
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
One-pass typed decisions (choice / yes-no / score)
Upstream model links: Maincode/matilda-jev-v1
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Rewrite prompts into MiniMax-H3 audio-video prompts
Upstream model links: lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA-8B · Qwen/Qwen3-VL-8B-Instruct
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Predict where to click on a screenshot from text
Upstream model links: merve/muse-glimmer-ft-clicking-v2 · meta-models/Muse-Glimmer-30B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
Embodied spatial reasoning, grounding & pointing VLM
Upstream model links: DeepCybo/PhysBrain1.5-2B
Community record · not individually tested
Publisher: hugging-apps
Publisher summary (original)
5/8-step distilled Qwen-Image-2.1 T2I + editing
Upstream model links: PrunaAI/Pruna-Qwen-Image-2.1 · Qwen/Qwen-Image-2.1
Declared repository license: other