---
license: apache-2.0
language:
- en
tags:
- Diffusion Transformer
- Image Editing
- Scepter
- ACE
---
ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
Tongyi Lab, Alibaba Group
[**Paper**](https://arxiv.org/abs/2410.00086) **|** [**Project Page**](https://ali-vilab.github.io/ace-page/) **|** [**Code**](https://github.com/ali-vilab/ACE)
ACE is a unified foundational model framework that supports a wide range of visual generation tasks.
By defining CU for unifying multi-modal inputs across different tasks and incorporating long-context CU,
we introduce historical contextual information into visual generation tasks, paving
the way for ChatGPT-like dialog systems in visual generation.
## 📢 News
* **[2024.9.30]** Release the paper of ACE on arxiv.
* **[2024.10.31]** Release the ACE checkpoint on [ModelScope](https://www.modelscope.cn/models/iic/ACE-0.6B-512px) and [HuggingFace](https://huggingface.co/scepter-studio/ACE-0.6B-512px).
* **[2024.11.1]** Support online demo on [HuggingFace](https://huggingface.co/spaces/scepter-studio/ACE-Chat).
* **[2024.11.20]** Release the [ACE-0.6b-1024px](https://huggingface.co/scepter-studio/ACE-0.6B-1024px) model,
which significantly enhances image generation quality compared with [ACE-0.6b-512px](https://huggingface.co/scepter-studio/ACE-0.6B-512px).
## 🚀 Installation
Install the necessary packages with `pip`:
```bash
git clone https://github.com/ali-vilab/ACE.git
pip install -r requirements.txt
```
## 🔥 ACE Models
| **Model** | **Status** |
|:----------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| ACE-0.6B-512px | [](https://huggingface.co/spaces/scepter-studio/ACE-Chat)
[](https://www.modelscope.cn/models/iic/ACE-0.6B-512px) [](https://huggingface.co/scepter-studio/ACE-0.6B-512px) |
| ACE-0.6B-1024px | [](https://huggingface.co/spaces/scepter-studio/ACE-Refiner-Chat)
[](https://www.modelscope.cn/models/iic/ACE-0.6B-1024px) [](https://huggingface.co/scepter-studio/ACE-0.6B-1024px) | |
| ACE-12B-FLUX-dev | Coming Soon |
## 🖼 Model Performance Visualization
The current model's parameters scale of ACE is 0.6B, which imposes certain limitations on the quality of image generation. [FLUX.1-Dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), on the other hand,
has a significant advantage in text-to-image generation quality. By using SDEdit, we can effectively leverage the generative capabilities of FLUX to further enhance the image results generated by ACE. Based on the above considerations, we have designed the ACE-Refiner pipeline, as shown in the diagram below.
As shown in the figure below, when the strength
σ of the generated image is high, the generated image will suffer from fidelity loss compared to the original image. Conversely, lower
σ does not significantly improve the image quality. Therefore, users can make a trade-off between fidelity to the generated result and the image quality based on their own needs.
Users can set the value of "REFINER_SCALE" in the configuration file `config/inference_config/models/ace_0.6b_1024_refiner.yaml`.
We recommend that users use the advance options in the [webui-demo](#-chat-bot-) for effect verification.
We compared the generation and editing performance of different models on several tasks, as shown as following.
## 🔥 Training
We offer a demonstration training YAML that enables the end-to-end training of ACE using a toy dataset. For a comprehensive overview of the hyperparameter configurations, please consult `config/ace_0.6b_512_train.yaml`.
### Prepare datasets
Please find the dataset class located in `modules/data/dataset/dataset.py`,
designed to facilitate end-to-end training using an open-source toy dataset.
Download a dataset zip file from [modelscope](https://www.modelscope.cn/models/iic/scepter/resolve/master/datasets/hed_pair.zip), and then extract its contents into the `cache/datasets/` directory.
Should you wish to prepare your own datasets, we recommend consulting `modules/data/dataset/dataset.py` for detailed guidance on the required data format.
### Prepare initial weight
The ACE checkpoint has been uploaded to both ModelScope and HuggingFace platforms:
* [ModelScope](https://www.modelscope.cn/models/iic/ACE-0.6B-512px)
* [HuggingFace](https://huggingface.co/scepter-studio/ACE-0.6B-512px)
In the provided training YAML configuration, we have designated the Modelscope URL as the default checkpoint URL. Should you wish to transition to Hugging Face, you can effortlessly achieve this by modifying the PRETRAINED_MODEL value within the YAML file (replace the prefix "ms://iic" to "hf://scepter-studio").
### Start training
You can easily start training procedure by executing the following command:
```bash
# ACE-0.6B-512px
PYTHONPATH=. python tools/run_train.py --cfg config/ace_0.6b_512_train.yaml
# ACE-0.6B-1024px
PYTHONPATH=. python tools/run_train.py --cfg config/ace_0.6b_1024_train.yaml
```
## 🚀 Inference
We provide a simple inference demo that allows users to generate images from text descriptions.
```bash
PYTHONPATH=. python tools/run_inference.py --cfg config/inference_config/models/ace_0.6b_512.yaml --instruction "make the boy cry, his eyes filled with tears" --seed 199999 --input_image examples/input_images/example0.webp
```
We recommend runing the examples for quick testing. Running the following command will run the example inference and the results will be saved in `examples/output_images/`.
```bash
PYTHONPATH=. python tools/run_inference.py --cfg config/inference_config/models/ace_0.6b_512.yaml
```
## 📝 Citation
```bibtex
@article{han2024ace,
title={ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer},
author={Han, Zhen and Jiang, Zeyinzi and Pan, Yulin and Zhang, Jingfeng and Mao, Chaojie and Xie, Chenwei and Liu, Yu and Zhou, Jingren},
journal={arXiv preprint arXiv:2410.00086},
year={2024}
}
``` 