Spaces

·

The AI App Directory

New Space Get PRO Learn more

Spaces of the week

13 Jul 2026

Hy3

Hy3 multi-turn streaming chat with function calling

Krea 2 Identity Edit

Identity-preserving instruction image editing on Krea 2

UniSE Speech Enhancement

Unified AR-LM-based speech enhancement & separation

GEPARD

Spotted text-to-speech with voice cloning and text-CFG

Pulpie

Clean HTML 20x faster — encoder vs decoder, live

SenseNova Vision

Analyze or generate images with AI-powered vision tasks

LingBot-Video MoE 30B-A3B

Embodied MoE video generation — T2V, I2V, T2I

All running apps, trending first

Bonsai 27B WebGPU Kernels

Run a 1-bit 27B LLM locally in your browser on WebGPU

Pro Realism Edit Studio

Powerful image editing - supports one or two input images.

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

Reproducing ICML 2026

Reproduce every ICML 2026 paper with your agent

10Eros LTX 2.3 Image-to-Video

10eros ltx 2.3 image-to-video with native audio

HF Realtime Voice

Voice chat over WebSocket against a HF speech-to-speech

Gemma Avatar

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

OvisOCR2

Stream structured Markdown from document images and PDFs.

Omni Image Editor

Image edit, text to image, image upscale, remove watermark

Krea 2 Identity Edit

Identity-preserving instruction image editing on Krea 2

Qwen-Image-Edit-2511-LoRAs-Fast

Demo of the Collection of Qwen Image Edit LoRAs

Z Image Turbo

Generate vivid images from text prompts in seconds

Wan2.2 14B Preview

generate a video from an image with a text prompt

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

An Open Realtime Voice You Can Actually Run Yourself

Generate real‑time spoken AI conversations

Unlimited OCR

Extract text from images and PDFs instantly

Pulpie

Clean HTML 20x faster — encoder vs decoder, live

UniSE Speech Enhancement

Unified AR-LM-based speech enhancement & separation

LingBot-Video MoE 30B-A3B

Embodied MoE video generation — T2V, I2V, T2I

Dream Motion Pro - Wan 2.2

Fast Wan 2.2 image-to-video with first/last frames

OmniVoice

High-quality voice cloning TTS for 600+ languages

FLUX.2 Klein multi-LoRA

Use multiple FLUX.2-Klein LoRAs

GEPARD

Spotted text-to-speech with voice cloning and text-CFG

Soofi S — Sovereign German-English Foundation Model

Soofi S 30B-A3B pretraining report project page