metadata

title: Real-Time Latent Consistency Model
emoji: 🔥
colorFrom: gray
colorTo: indigo
sdk: docker
pinned: false

Real-Time Latent Consistency Model

This demo showcases Latent Consistency Model (LCM) using Diffusers with a MJPEG stream server.

You need a webcam to run this demo. 🤗

Running Locally

You need CUDA and Python
TIMEOUT: limit user session timeout SAFETY_CHECKER: disabled if you want NSFW filter off
MAX_QUEUE_SIZE: limit number of users on current app instance

python -m venv venv 
source venv/bin/activate 
pip install -r requirements.txt
uvicorn "app:app" --host 0.0.0.0 --port 7860 --reload

or with environment variables

TIMEOUT=120 SAFETY_CHECKER=True MAX_QUEUE_SIZE=4 uvicorn "app:app" --host 0.0.0.0 --port 7860 --reload

If you're running locally and want to test it on Mobile Safari, the webserver needs to be served over HTTPS.

openssl req -newkey rsa:4096 -nodes -keyout key.pem -x509 -days 365 -out certificate.pem
uvicorn "app:app" --host 0.0.0.0 --port 7860 --reload --log-level info --ssl-certfile=certificate.pem --ssl-keyfile=key.pem

Docker

You need NVIDIA Container Toolkit for Docker

docker build -t lcm-live .
docker run -ti -p 7860:7860 --gpus all lcm-live

or with environment variables

docker run -ti -e TIMEOUT=0 -e SAFETY_CHECKER=False -p 7860:7860 --gpus all lcm-live

Demo on Hugging Face

https://huggingface.co/spaces/radames/Real-Time-Latent-Consistency-Model