Demos

790 in the directory.

Find interactive AI demos for text, images, speech and video. Filter by task and last observed status, then open a demo profile.

Most liked A–Z Recently synced

Status reflects the last source check, not a live availability guarantee. Open a demo for its details.

Voice-Cloning BilalSardar Voice Cloning mit · gradio sleeping last observed
dreamgaussian jiawei011 Paper is from https://arxiv.org/abs/2309.16653 text to image · mit · gradio unavailable last observed
Face-Real-ESRGAN doevent Face Real ESRGAN 2x 4x 8x demo for Real-ESRGAN mcp server · apache-2.0 · gradio sleeping last observed
PuLID-FLUX yanze PuLID — text to image demo text to image · apache-2.0 · gradio running last observed
HiDream-I1-Dev HiDream-ai HiDream I1 Dev demo for HiDream-I1-Dev mit · gradio running last observed
GLM-130B zai-org GLM 130B demo for GLM-130B apache-2.0 · gradio running last observed
Qwen-Image-Layered Qwen Qwen Image Layered — text generation demo text generation · apache-2.0 · gradio running last observed
anime-remove-background skytnt Anime Remove Background demo for anime-seg apache-2.0 · gradio running last observed
point-e openai Point E license unknown · gradio unavailable last observed
chatterbox-turbo-demo ResembleAI Chatterbox Turbo Demo mcp server · mit · gradio running last observed
Seed-VC Plachta Seed Voice Conversion — text to speech demo text to speech · gpl-3.0 · gradio running last observed
animagine-xl-4.0 Asahina2K The Ultimate Anime-themed SDXL model text to image · mit · gradio running last observed
text-to-speech k2-fsa Text-to-speech (TTS) with Next-gen Kaldi text to speech · apache-2.0 · gradio running last observed
AICoverGen r3gm AICoverGen demo for kitlemonfoot_rvc_models mit · gradio running last observed
dreambooth-training multimodalart Dreambooth Training — text to image demo text to image · mit · gradio running last observed
flux-lora-lab multimodalart FLUX LoRa Lab — text to image demo text to image · mit · gradio running last observed
InstantCharacter InstantX InstantCharacter — text to image demo text to image · apache-2.0 · gradio running last observed
florence-sam SkalskiP Florence2 + SAM2 demo for Florence-2-base apache-2.0 · gradio running last observed
finegrain-object-cutter finegrain Create HD cutouts from any image with just a prompt mit · gradio running last observed
seamless-m4t-v2-large facebook Seamless M4T v2 demo for seamless-m4t-v2-large license unknown · docker unavailable last observed
LLM-Model-VRAM-Calculator NyxKrage LLM Model VRAM Calculator demo for Starling-LM-7B-beta mit · static running last observed
latentdiffusion mediasynthesismuseum Latent Diffusion demo for compvis-latent-diffusion-text2img-large mit · gradio running last observed
marigold prs-eth This is a demo of the monocular depth estimation pipeline, described in the CVPR 2024 paper titled… apache-2.0 · gradio running last observed
stable-virtual-camera stabilityai - **Project Page**: https://stable-virtual-camera.github.io/ - **Paper**: http://arxiv.org/abs/2503… text to image · license unknown · gradio unavailable last observed
StableVicuna CarperAI StableVicuna demo for stable-vicuna-13b-delta cc-by-nc-4.0 · gradio sleeping last observed
synthetic-generation strova-ai Privacy-safe synthetic data for ML and data augmentation mit · static running last observed
DeepSeek-OCR-Demo merterbak Try out DeepSeek-OCR-2 on your PDFs or images mit · gradio running last observed
InternVL OpenGVLab - **Repository:** InternVL - **Paper:** 2404.16821 - **Models:** OpenGVLab/InternVL2-1B, OpenGVLab/… text to image · mit · gradio running last observed
robot-learning-tutorial lerobot An interactive version of the arxiv.org/abs/2510.12403 paper research article template · license unknown · docker running last observed
stable-diffusion-xl-inpainting diffusers SDXL Inpainting — text to image demo text to image · license unknown · gradio running last observed
guanaco-playground-tgi uwnlp Guanaco Playground Tgi demo for bloom license unknown · gradio running last observed
RWKV-Gradio-1 BlinkDL RWKV-Gradio-1 — zero shot classification demo zero shot classification · apache-2.0 · gradio running last observed
AnimateDiff guoyww AnimateDiff — text to image demo text to image · apache-2.0 · gradio unavailable last observed
AI-WebTV jbilcke-hf A generative AI WebTV, powered by Zeroscope and Hugging Face. license unknown · docker sleeping last observed
Image-to-Line-Drawings awacke1 ✏️Image2Drawing mit · gradio running last observed
LocateAnything nvidia Official demo for **LocateAnything**: locate any object in images or videos with natural language. license unknown · gradio running last observed