radames/Real-Time-Latent-Consistency-Model
A Gradio demo app providing real-time image-to-image and text-to-image generation using Latent Consistency Models with MJPEG streaming.
Not currently ranked — collecting fresh signals.
star history
This repository demonstrates the Latent Consistency Model (LCM) and its LoRA variants using the Diffusers library. It provides multiple pipelines including text-to-image, image-to-image, and ControlNet-guided generation. The app runs a local server with MJPEG streaming for real-time webcam-based generation, supporting as few as 4 inference steps via LCM-LoRA acceleration. It supports both SD 1.5 and SDXL models.
Frequently asked
- What is radames/Real-Time-Latent-Consistency-Model?
- A Gradio demo app providing real-time image-to-image and text-to-image generation using Latent Consistency Models with MJPEG streaming.
- Is Real-Time-Latent-Consistency-Model open source?
- Yes — radames/Real-Time-Latent-Consistency-Model is open source, released under the Apache-2.0 license.
- What language is Real-Time-Latent-Consistency-Model written in?
- radames/Real-Time-Latent-Consistency-Model is primarily written in Python.
- How popular is Real-Time-Latent-Consistency-Model?
- radames/Real-Time-Latent-Consistency-Model has 916 stars on GitHub.
- Where can I find Real-Time-Latent-Consistency-Model?
- radames/Real-Time-Latent-Consistency-Model is on GitHub at https://github.com/radames/Real-Time-Latent-Consistency-Model.