# flowtyone/flowty-realtime-lcm-canvas

A realtime sketch to image demo using LCM and the gradio library.

Repository: https://github.com/flowtyone/flowty-realtime-lcm-canvas
Canonical: https://ross.abutalabs.com/products/flowty-realtime-lcm-canvas
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2023-12-02T14:38:42+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1019, "days_push": 1005, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1771, forks 148 (observed 2026-08-28T04:05:34.134766+00:00)

## What it is
A real-time sketch-to-image demo application that uses Latent Consistency Models (LCM) with a Gradio web UI. Users draw on a canvas and see AI-generated images rendered near-instantly, with support for swapping in different models via LCM LoRA.

## Use cases
- turn sketches into images in real time
- demo latent consistency model image generation
- draw on a canvas and see AI renders instantly
- try different stable diffusion models with LCM LoRA
- run a local sketch-to-image web app on a GPU
- run the demo in Google Colab

## When to choose
- you want an interactive realtime sketch-to-image demo
- you have a capable GPU (e.g. RTX 4090 or Apple M-series) and want local inference
- you want a simple Gradio-based playground for LCM models

## When to avoid
- you need production image generation pipelines
- you lack a GPU and cannot tolerate slow inference
- you need fine-grained control over diffusion parameters or custom training

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, llm-inference, gui
- domain: artificial-intelligence, image-processing, graphics, deep-learning
- platform: python, cross-platform
- tags: stable-diffusion, lcm, lcm-lora, gradio, sketch-to-image, realtime-generation, canvas, demo, gpu

## Member repositories
- flowtyone/flowty-realtime-lcm-canvas (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.134766+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:26:00.165764+00:00, confidence not recorded.
  - readme: https://github.com/flowtyone/flowty-realtime-lcm-canvas (fetched 2026-08-28T04:05:34.134766+00:00, sha 0c48ae4b4ef2)
- Data as of 2026-08-30T08:39:29.467469+00:00.