🪄SCEPTER is an open-source code repository dedicated to generative training, fine-tuning, and inference, encompassing a suite of downstream tasks such as image generation, transfer, editing. SCEPTER integrates popular community-driven implementations as well as proprietary methods by Tongyi Lab of Alibaba Group, offering a comprehensive toolkit for researchers and practitioners in the field of AIGC. This versatile library is designed to facilitate innovation and accelerate development in the rapidly evolving domain of generative models.
SCEPTER offers 3 core components:
Clay Style
, De-Text
, Segmentation
, etc.Text-Based Style Editing
.zoom-out
, virtual try on
, inpainting
.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.
conda
command:conda env create -f environment.yaml
conda activate scepter
pip
command:We recommend installing the specific version of PyTorch and accelerate toolbox xFormers. You can install these recommended version by pip:
pip install -r requirements/recommended.txt
pip install scepter
Documentation | Key Features |
---|---|
Train | DDP / FSDP / FairScale / Xformers |
Inference | Dynamic load/unload |
Dataset Management | Local / Http / OSS / Modelscope |
Tasks | Methods | Links |
---|---|---|
Text-to-image generation | SD v1.5 | |
Text-to-image generation | SD v2.1 | |
Text-to-image generation | SD-XL | |
Efficient Tuning | LoRA | |
Efficient Tuning | Res-Tuning(NeurIPS23) | |
Controllable image synthesis | 🌟SCEdit(CVPR24) | |
Image editing | 🌟LAR-Gen | |
Image editing | 🌟StyleBooth |
To fully experience SCEPTER Studio, you can launch the following command line:
pip install scepter
python -m scepter.tools.webui
or run after clone repo code
git clone https://github.com/modelscope/scepter.git
PYTHONPATH=. python scepter/tools/webui.py --cfg scepter/methods/studio/scepter_ui.yaml
The startup of SCEPTER Studio eliminates the need for manual downloading and organizing of models; it will automatically load the corresponding models and store them in a local directory. Depending on the network and hardware situation, the initial startup usually requires 15-60 minutes, primarily involving the download and processing of SDv1.5, SDv2.1, and SDXL models. Therefore, subsequent startups will become much faster (about one minute) as downloading is no longer required.
Image Editing | Training | Model Sharing | Model Inference | Data Management |
---|---|---|---|---|
We deploy a work studio on Modelscope that includes only the inference tab, please refer to ms_scepter_studio and hf_scepter_studio
Alibaba TongYi Vision Intelligence Lab
Discover more about open-source projects on image generation, video generation, and editing tasks.
ModelScope Library is the model library of ModelScope project, which contains a large number of popular models.
SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning) is an extensible framwork designed to faciliate lightweight model fine-tuning and inference.
If our work is useful for your research, please consider citing:
@misc{scepter,
title = {SCEPTER, https://github.com/modelscope/scepter},
author = {SCEPTER},
year = {2023}
}
This project is licensed under the Apache License (Version 2.0).
Thanks to Stability-AI, SWIFT library and Fooocus for their awesome work.