HF Realtime Voice
Voice chat over WebSocket against a HF speech-to-speech
Voice chat over WebSocket against a HF speech-to-speech
On-device PII redaction by National Design Studio
4D face reconstruction & tracking from an image sequence
Unifying Controlled Character Animation
Drag the sun around a 3D ball to relight outdoor photos
Train Krea 2 LoRAs on your images via HF Jobs
Extract text from images and PDFs
Talk to Gemma 4 face to face, with a 3D lip-synced avatar
Voice chat over WebSocket against a HF speech-to-speech
Powerful image editing - supports one or two input images.
generate a video from an image with a text prompt
Extract text from images and PDFs instantly
generate a video from an image with a text prompt
Chat with Gemma 4 E2B AI model in your browser
Protect Birds
Krea 2 text-to-image (Raw + Turbo)
A small LLM writes, draws & directs original ASCII films
Use multiple FLUX.2-Klein LoRAs
10eros ltx 2.3 image-to-video with native audio
Evolving an agent's harness, not its model, on Harvey's LAB
WAN2.2 based I2V
Demo of the Collection of Qwen Image Edit LoRAs
generate a video from an image with a text prompt
Generate high-quality images from text prompts
Detect and label objects in images and videos
Image edit, text to image, image upscale, remove watermark
Claim your Build Small Hackathon certificate
generate a video from an image with a text prompt
An Open Source Cyber Security Agent
Chat with an AI coding assistant that explains its reasoning
Run LFM2.5 230M with custom WebGPU kernels
text to video, image to video, video extend