Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
| Date | Stars |
|---|---|
| 2026-07-24 | 2466 |
| 2026-07-25 | 2466 |
| 2026-07-28 | 2466 |
| 2026-07-30 | 2466 |
| 2026-07-31 | 2466 |
| 2026-08-06 | 2466 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# img2img-turbo
[**Paper**](https://arxiv.org/abs/2403.12036) | [**Sketch2Image Demo**](https://huggingface.co/spaces/gparmar/img2img-turbo-sketch)
#### **Quick start:** [**Running Locally**](#getting-started) | [**Gradio (locally hosted)**](#gradio-demo) | [**Training**](#training-with-your-own-data)
### Cat Sketching
<p align="left" >
<img src="https://raw.githubusercontent.com/GaParmar/img2img-turbo/main/assets/cat_2x.gif" width="800" />
</p>
### Fish Sketching
<p align="left">
<img src="https://raw.githubusercontent.com/GaParmar/img2img-turbo/main/assets/fish_2x.gif" width="800" />
</p>
We propose a general method for adapting a single-step diffusion model, such as SD-Turbo, to new tasks and domains through adversarial learning. This enables us to leverage the internal knowledge of pre-trained diffusion models while achieving efficient inference (e.g., for 512x512 images, 0.29 seconds on A6000 and 0.11 seconds on A100).
Our one-step conditional models **CycleGAN-Turbo** and **pix2pix-turbo** can perform various image-to-image translation tasks for both unpaired and paired settings. CycleGAN-Turbo outperforms existing GAN-based and diffusion-based methods, while pix2pix-turbo is on par with recent works such as ControlNet for Sketch2Photo and Edge2Image, but with one-step inference.
[One-Step Image Translation with Text-to-Image Models](https://arxiv.org/abs/2403.12036)<br>
[Gaurav Parmar](https://gauravparmar.com/), [Taesung Park](https://taesung.me/), [Srinivasa Narasimhan](https://www.cs.cmu.edu/~srinivas/), [Jun-Yan Zhu](https://github.com/junyanz/)<br>
CMU and Adobe, arXiv 2403.12036
<br>
<div>
<p align="center">
<img src='assets/teaser_results.jpg' align="center" width=1000px>
</p>
</div>
## Results
### Paired Translation with pix2pix-turbo
**Edge to Image**
<div>
<p align="center">
<img src='assets/edge_to_image_results.jpg' align="center" width=800px>
</p>
</div>
<!-- **Sketch to Image**
TODO -->
### Generating Diverse Outputs
By varying the input noise map, our method can generate diverse outputs from the same input conditioning.
The output style can be controlled by changing the text prompt.
<div> <p align="center">
<img src='assets/gen_variations.jpg' align="center" width=800px>
</p> </div>
### Unpaired Translation with CycleGAN-Turbo
**Day to Night**
<div> <p align="center">
<img src='assets/day2night_results.jpg' align="center" width=800px>
</p> </div>
**Night to Day**
<div><p align="center">
<img src='assets/night2day_results.jpg' align="center" width=800px>
</p> </div>
**Clear to Rainy**
<div>
<p align="center">
<img src='assets/clear2rainy_results.jpg' align="center" width=800px>
</p>
</div>
**Rainy to Clear**
<div>
<p align="center">
<img src='assets/rainy2clear.jpg' align="center" width=800px>
</p>
</div>
<hr>
## Method
**Our Generator Architecture:**
We tightly integrate three separate modules in the original latent diffusion models into a single end-to-end network with small trainable weights. This architecture allows us to translate the input image x to the output y, while retaining the input scene structure. We use LoRA adapters in each module, introduce skip connections and Zero-Convs between input and output, and retrain the first layer of the U-Net. Blue boxes indicate trainable layers. Semi-transparent layers are frozen. The same generator can be used for various GAN objectives.
<div>
<p align="center">
<img src='assets/method.jpg' align="center" width=900px>
</p>
</div>
## Getting Started
**Environment Setup**
- We provide a [conda env file](environment.yaml) that contains all the required dependencies.
```
conda env create -f environment.yaml
```
- Following this, you can activate the conda environment with the command below.
```
conda activate img2img-turbo
```
- Or use virtual environment:
```
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
**Paired Image Translation (pix2pix-turbo)**
- The following commaExcerpt of 8,443 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:77cc37928d59dfc0, topic:stable-diffusion, topic:generative-art, readme:text-to-image
