Spaces

·

The AI App Directory

New Space Get PRO Learn more

Spaces of the week

20 Jul 2026

Bonsai 27B WebGPU Kernels

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

Gemma 4 - Vision Token Budget

Resize images for visual token budgets while keeping aspect ratio

Nemotron-Labs-Audex

Unified audio-text intelligence

Krea 2 Identity Edit

Identity-preserving instruction image editing on Krea 2

Krea 2 Outpaint

Extend images into larger canvases with Krea 2 outpaint

OvisOCR2

Stream structured Markdown from document images and PDFs.

MOSS-VL-Realtime

Realtime VLM for image and video understanding

LTX-Best-Face-ID

Distilled LTX-2.3 identity video from a reference photo

All running apps, trending first

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

Bonsai 27B WebGPU Kernels

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

Reproducing ICML 2026

Reproduce every ICML 2026 paper with your agent

Qwen-Image-Edit-2511-LoRAs-Fast

Demo of the Collection of Qwen Image Edit LoRAs

HF Realtime Voice

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

Unlimited OCR

Extract text from images and PDFs instantly

Krea 2 Identity Edit

Identity-preserving instruction image editing on Krea 2

Mage-Flow

Efficient native-resolution image generation and editing

Omni Image Editor

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

WANMAN

WAN2.2 based I2V

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

Krea 2 Outpaint

Extend images into larger canvases with Krea 2 outpaint

FLUX.2 Klein multi-LoRA

Use multiple FLUX.2-Klein LoRAs

Gemma Avatar

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

T-Search: an open agentic retriever

Open agentic retriever for hard multi-step search

Z Image Turbo

Generate vivid images from text prompts in seconds

Inflect v2 — Tiny Local TTS

Run complete 3.96M and 9.36M text-to-waveform models live.

Wan2.2 14B Fast Preview [NEW]

Animate an image into a video with custom prompts

TRELLIS.2

High-fidelity 3D Generation from images

LTX 2.3 10Eros Image-to-Video

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

Dream Motion Pro - Wan 2.2

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

OvisOCR2

Stream structured Markdown from document images and PDFs.

UniSE Speech Enhancement

Unified AR-LM-based speech enhancement & separation

Qwen3-TTS Demo

Generate speech from text using voice design, cloning or presets