# GaParmar/img2img-turbo

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

Repository: https://github.com/GaParmar/img2img-turbo
Canonical: https://ross.abutalabs.com/products/img2img-turbo
Language: Python
License: MIT
License Family: permissive
Topics: computer-vision, deep-learning, generative-adversarial-network, generative-art, stable-diffusion
Last push: 2025-08-01T20:39:35+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 34, release rhythm 35, longevity 65
- inputs: {"age_days": 922, "days_push": 397, "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 2476, forks 291 (observed 2026-08-28T04:06:55.037849+00:00)

## What it is
A research library implementing one-step image-to-image translation models (CycleGAN-Turbo and pix2pix-turbo) built on SD-Turbo diffusion models adapted via adversarial learning. It supports tasks like sketch-to-image, edge-to-image, and day-to-night translation with fast single-step inference.

## Use cases
- convert sketches to photorealistic images
- translate day photos to night and vice versa
- generate images from edge maps with a text prompt
- run fast one-step image-to-image translation on GPU
- train custom image translation models on my own paired or unpaired data
- make clear photos look rainy

## When to choose
- you need fast (sub-second) image-to-image translation with diffusion quality
- you want to adapt a single-step diffusion model to a new domain via adversarial training
- you need both paired (pix2pix) and unpaired (CycleGAN) translation in one toolkit

## When to avoid
- you need multi-step high-fidelity diffusion pipelines with fine-grained control
- you have no GPU available
- you want a polished end-user application rather than a research codebase

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, llm-inference
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, windows
- tags: stable-diffusion, image-to-image, diffusion-models, pix2pix, cyclegan, generative-ai, sketch-to-image, adversarial-learning, gradio, gpu, linux, macos

## Member repositories
- GaParmar/img2img-turbo (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:55.037849+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 2026-08-30T02:28:21.411063+00:00, confidence not recorded.
  - readme: https://github.com/GaParmar/img2img-turbo (fetched 2026-08-28T04:06:55.037849+00:00, sha 7020f8642d22)
- Data as of 2026-08-30T08:39:29.467469+00:00.