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 2 / 417
Community record · not individually tested
Publisher: fffiloni
Publisher summary (original)
Easily expand image boundaries
Upstream model links: madebyollin/sdxl-vae-fp16-fix · SG161222/RealVisXL_V5.0_Lightning · TencentARC/T2I-Adapter · xinsir/controlnet-union-sdxl-1.0
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: suno
Upstream model links: suno/bark
Declared repository license: cc-by-nc-4.0
Community record · not individually tested
Publisher: AI4Editing
Upstream model links: LiuZichen/MagicQuill-models · lllyasviel/ControlNet · openai/clip-vit-large-patch14 · TencentARC/T2I-Adapter
Declared repository license: cc-by-nc-4.0
Community record · not individually tested
Publisher: Qwen
Upstream model links: Qwen/Qwen3-TTS-12Hz-1.7B-Base · Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice · Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: tencent
Publisher summary (original)
Image-to-3D Generation
Upstream model links: facebook/dinov2-giant · openai/shap-e · PixArt-alpha/PixArt-alpha · Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers-Distilled
Community record · not individually tested
Publisher: linoyts
Publisher summary (original)
Fast 4 step inference with Qwen Image Edit 2509
Upstream model links: dx8152/Qwen-Edit-2509-Multiple-angles · huggingface/documentation-images · kernels-community/vllm-flash-attn3 · linoyts/Qwen-Image-Edit-Rapid-AIO
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: microsoft
Publisher summary (original)
High-fidelity 3D Generation from images
Upstream model links: microsoft/TRELLIS.2-4B · ZhengPeng7/BiRefNet
Declared repository license: mit
Community record · not individually tested
Publisher: finegrain
Publisher summary (original)
Clarity AI Upscaler Reproduction
Upstream model links: refiners/juggernaut.reborn.sd1_5.unet · refiners/juggernaut.reborn.sd1_5.autoencoder · refiners/juggernaut.reborn.sd1_5.text_encoder · refiners/controlnet.sd1_5.tile
Declared repository license: mit
Community record · not individually tested
Publisher: Wan-AI
Publisher summary (original)
Wan: Open and Advanced Large-Scale Video Generative Models
Declared repository license: mit
Community record · not individually tested
Publisher: r3gm
Publisher summary (original)
generate a video from an image with a text prompt
Upstream model links: BlinkDL/rwkv7-g1 · cbensimon/WanTransformer3DModel-sm120-cu130-raa · hfmlsoc/ncii-guard-v02 · iahhnim/ESRGAN_collection
Community record · not individually tested
Publisher: yisol
Publisher summary (original)
High-fidelity Virtual Try-on
Upstream model links: stabilityai/stable-diffusion-xl-base-1.0 · yisol/IDM-VTON
Declared repository license: cc-by-nc-sa-4.0
Community record · not individually tested
Publisher: yanze
Upstream model links: black-forest-labs/FLUX.1-dev · black-forest-labs/FLUX.1-Krea-dev · black-forest-labs/FLUX.1-schnell · ByteDance/SDXL-Lightning
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: Gustavosta
Upstream model links: Gustavosta/MagicPrompt-Stable-Diffusion · openai-community/gpt2
Declared repository license: mit
Community record · not individually tested
Publisher: stabilityai
Publisher summary (original)
Generate images with SD3.5
Upstream model links: stabilityai/stable-diffusion-3.5-large
Declared repository license: other
Community record · not individually tested
Publisher: mediasynthesismuseum
Upstream model links: multimodalart/stable-video-diffusion · stabilityai/stable-video-diffusion-img2vid-xt
Declared repository license: other
Community record · not individually tested
Publisher: deepseek-ai
Publisher summary (original)
A unified multimodal understanding and generation model.
Upstream model links: deepseek-ai/Janus-Pro-7B · ai-forever/Real-ESRGAN
Declared repository license: mit
Community record · not individually tested
Publisher: huggingface-projects
Publisher summary (original)
QR Code AI Art Generator Blend QR codes with AI Art
Upstream model links: DionTimmer/controlnet_qrcode-control_v1p_sd15 · runwayml/stable-diffusion-v1-5
Community record · not individually tested
Publisher: TencentARC
Upstream model links: google/ddpm-celebahq-256 · SG161222/RealVisXL_V3.0 · TencentARC/PhotoMaker · TencentARC/PhotoMaker-V2
Declared repository license: apache-2.0
Community record · not individually tested
Publisher: fancyfeast
Upstream model links: google/siglip-so400m-patch14-384
Community record · not individually tested
Publisher: nari-labs
Publisher summary (original)
Generate realistic dialogue from a script, using Dia!
Upstream model links: nari-labs/Dia-1.6B-0626
Community record · not individually tested
Publisher: NihalGazi
Publisher summary (original)
Free Text-To-Speech generator with Emotion control (OpenAI)
Community record · not individually tested
Publisher: ResembleAI
Publisher summary (original)
Expressive Zeroshot TTS
Upstream model links: ResembleAI/chatterbox
Community record · not individually tested
Publisher: jasperai
Upstream model links: black-forest-labs/FLUX.1-dev · jasperai/Flux.1-dev-Controlnet-Upscaler
Declared repository license: other
Community record · not individually tested
Publisher: multimodalart
Upstream model links: stabilityai/stable-cascade · stabilityai/stable-cascade-prior
Declared repository license: mit