Spaces

·

The AI App Directory

New Space Get PRO Learn more

Spaces of the week

6 Jul 2026

HF Realtime Voice

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

Rampart

On-device PII redaction by National Design Studio

FaceAnything

4D face reconstruction & tracking from an image sequence

SCAIL 2

Unifying Controlled Character Animation

Sun Direction Flux Klein

Drag the sun around a 3D ball to relight outdoor photos

Krea 2 LoRA Trainer

Train Krea 2 LoRAs on your images via HF Jobs

Unlimited OCR

Extract text from images and PDFs

Gemma Avatar

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

All running apps, trending first

HF Realtime Voice

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

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

Unlimited OCR

Extract text from images and PDFs instantly

ProtectBirds

Protect Birds

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

Krea 2

Krea 2 text-to-image (Raw + Turbo)

Gemma 4 WebGPU Kernels

Chat with Gemma 4 E2B AI model in your browser

Don't Train the Model, Evolve the Harness

Evolving an agent's harness, not its model, on Harvey's LAB

Wan2.2 14B Fast Preview

generate a video from an image with a text prompt

Qwen-Image-Edit-2511-LoRAs-Fast

Demo of the Collection of Qwen Image Edit LoRAs

WANMAN

WAN2.2 based I2V

FLUX.2 Klein multi-LoRA

Use multiple FLUX.2-Klein LoRAs

LLM Cinema

A small LLM writes, draws & directs original ASCII films

10Eros LTX 2.3 Image-to-Video

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

Wan2.2 14B Preview

generate a video from an image with a text prompt

Z Image Turbo

Generate high-quality images from text prompts

Gemma Avatar

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

Omni Image Editor

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

LocateAnything

Detect and label objects in images and videos

Wan2.2 14B Fast

generate a video from an image with a text prompt

RL-for-LLMs Wiki

Agents collaboratively build an expert-level, citation-backe

RL-for-LLMs Wiki

A beautiful reader for the RL-for-LLMs knowledge base

LFM2 WebGPU Kernels

Run LFM2.5 230M with custom WebGPU kernels