|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
--- |
|
<div align="center"> |
|
|
|
[//]: # (<h1>CSGO: Content-Style Composition in Text-to-Image Generation</h1>) |
|
|
|
[//]: # () |
|
[//]: # ([**Peng Xing**](https://github.com/xingp-ng)<sup>12*</sup> · [**Haofan Wang**](https://haofanwang.github.io/)<sup>1*</sup> · [**Yanpeng Sun**](https://scholar.google.com.hk/citations?user=a3FI8c4AAAAJ&hl=zh-CN&oi=ao/)<sup>2</sup> · [**Qixun Wang**](https://github.com/wangqixun)<sup>1</sup> · [**Xu Bai**](https://huggingface.co/baymin0220)<sup>1</sup> · [**Hao Ai**](https://github.com/aihao2000)<sup>13</sup> · [**Renyuan Huang**](https://github.com/DannHuang)<sup>14</sup> · [**Zechao Li**](https://zechao-li.github.io/)<sup>2✉</sup>) |
|
|
|
[//]: # () |
|
[//]: # (<sup>1</sup>InstantX Team · <sup>2</sup>Nanjing University of Science and Technology · <sup>3</sup>Beihang University · <sup>4</sup>Peking University) |
|
|
|
[//]: # (<sup>*</sup>equal contributions, <sup>✉</sup>corresponding authors) |
|
|
|
<a href='https://csgo-gen.github.io/'><img src='https://img.shields.io/badge/Project-Page-green'></a> |
|
<a href='https://arxiv.org/abs/2408.16766'><img src='https://img.shields.io/badge/Technique-Report-red'></a> |
|
[](https://huggingface.co/spaces/xingpng/CSGO/) |
|
[](https://huggingface.co/spaces/InstantX/CSGO) |
|
|
|
|
|
</div> |
|
|
|
|
|
[//]: # (## Updates 🔥) |
|
|
|
[//]: # () |
|
[//]: # ([//]: # (- **`2024/07/19`**: ✨ We support 🎞️ portrait video editing (aka v2v)! More to see [here](assets/docs/changelog/2024-07-19.md).)) |
|
[//]: # () |
|
[//]: # ([//]: # (- **`2024/07/17`**: 🍎 We support macOS with Apple Silicon, modified from [jeethu](https://github.com/jeethu)'s PR [#143](https://github.com/KwaiVGI/LivePortrait/pull/143).)) |
|
[//]: # () |
|
[//]: # ([//]: # (- **`2024/07/10`**: 💪 We support audio and video concatenating, driving video auto-cropping, and template making to protect privacy. More to see [here](assets/docs/changelog/2024-07-10.md).)) |
|
[//]: # () |
|
[//]: # ([//]: # (- **`2024/07/09`**: 🤗 We released the [HuggingFace Space](https://huggingface.co/spaces/KwaiVGI/liveportrait), thanks to the HF team and [Gradio](https://github.com/gradio-app/gradio)!)) |
|
[//]: # ([//]: # (Continuous updates, stay tuned!)) |
|
[//]: # (- **`2024/08/30`**: 😊 We released the initial version of the inference code.) |
|
|
|
[//]: # (- **`2024/08/30`**: 😊 We released the technical report on [arXiv](https://arxiv.org/pdf/2408.16766)) |
|
|
|
[//]: # (- **`2024/07/15`**: 🔥 We released the [homepage](https://csgo-gen.github.io).) |
|
|
|
[//]: # () |
|
[//]: # (## Plan 💪) |
|
|
|
[//]: # (- [x] technical report) |
|
|
|
[//]: # (- [x] inference code) |
|
|
|
[//]: # (- [ ] pre-trained weight) |
|
|
|
[//]: # (- [ ] IMAGStyle dataset) |
|
|
|
[//]: # (- [ ] training code) |
|
|
|
## Introduction 📖 |
|
This repo, named **CSGO**, contains the official PyTorch implementation of our paper [CSGO: Content-Style Composition in Text-to-Image Generation](https://arxiv.org/abs/2408.16766). |
|
We are actively updating and improving this repository. If you find any bugs or have suggestions, welcome to raise issues or submit pull requests (PR) 💖. |
|
|
|
## Detail ✨ |
|
We currently release two model weights. |
|
|
|
| Mode | content token | style token | Other | |
|
|:----------------:|:-----------:|:-----------:|:---------------------------------:| |
|
| csgo.bin |4|16| - | |
|
| csgo_4_32.bin |4|32| Deepspeed zero2 | |
|
| csgo_4_32_v2.bin |4|32| Deepspeed zero2+more(coming soon) | |
|
|
|
|
|
## Pipeline 💻 |
|
<p align="center"> |
|
<img src="assets/image3_1.jpg"> |
|
</p> |
|
|
|
## Capabilities 🚅 |
|
|
|
🔥 Our CSGO achieves **image-driven style transfer, text-driven stylized synthesis, and text editing-driven stylized synthesis**. |
|
|
|
🔥 For more results, visit our <a href="https://csgo-gen.github.io"><strong>homepage</strong></a> 🔥 |
|
|
|
<p align="center"> |
|
<img src="assets/vis.jpg"> |
|
</p> |
|
|
|
|
|
## Getting Started 🏁 |
|
### 1. Clone the code and prepare the environment |
|
```bash |
|
git clone https://github.com/instantX-research/CSGO |
|
cd CSGO |
|
|
|
# create env using conda |
|
conda create -n CSGO python=3.9 |
|
conda activate CSGO |
|
|
|
# install dependencies with pip |
|
# for Linux and Windows users |
|
pip install -r requirements.txt |
|
``` |
|
|
|
### 2. Download pretrained weights(coming soon) |
|
|
|
The easiest way to download the pretrained weights is from HuggingFace: |
|
```bash |
|
# first, ensure git-lfs is installed, see: https://docs.github.com/en/repositories/working-with-files/managing-large-files/installing-git-large-file-storage |
|
git lfs install |
|
# clone and move the weights |
|
git clone https://huggingface.co/InstantX/CSGO |
|
``` |
|
Our method is fully compatible with [SDXL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), [VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix), [ControlNet](https://huggingface.co/TTPlanet/TTPLanet_SDXL_Controlnet_Tile_Realistic), and [Image Encoder](https://huggingface.co/h94/IP-Adapter/tree/main/sdxl_models/image_encoder). |
|
Please download them and place them in the ./base_models folder. |
|
|
|
tips:If you expect to load Controlnet directly using ControlNetPipeline as in CSGO, do the following: |
|
```bash |
|
git clone https://huggingface.co/TTPlanet/TTPLanet_SDXL_Controlnet_Tile_Realistic |
|
mv TTPLanet_SDXL_Controlnet_Tile_Realistic/TTPLANET_Controlnet_Tile_realistic_v2_fp16.safetensors TTPLanet_SDXL_Controlnet_Tile_Realistic/diffusion_pytorch_model.safetensors |
|
``` |
|
### 3. Inference 🚀 |
|
|
|
```python |
|
import torch |
|
from ip_adapter.utils import resize_content |
|
import numpy as np |
|
from ip_adapter.utils import BLOCKS as BLOCKS |
|
from ip_adapter.utils import controlnet_BLOCKS as controlnet_BLOCKS |
|
from PIL import Image |
|
from diffusers import ( |
|
AutoencoderKL, |
|
ControlNetModel, |
|
StableDiffusionXLControlNetPipeline, |
|
|
|
) |
|
from ip_adapter import CSGO |
|
|
|
|
|
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") |
|
|
|
base_model_path = "./base_models/stable-diffusion-xl-base-1.0" |
|
image_encoder_path = "./base_models/IP-Adapter/sdxl_models/image_encoder" |
|
csgo_ckpt = "./CSGO/csgo.bin" |
|
pretrained_vae_name_or_path ='./base_models/sdxl-vae-fp16-fix' |
|
controlnet_path = "./base_models/TTPLanet_SDXL_Controlnet_Tile_Realistic" |
|
weight_dtype = torch.float16 |
|
|
|
|
|
vae = AutoencoderKL.from_pretrained(pretrained_vae_name_or_path,torch_dtype=torch.float16) |
|
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16,use_safetensors=True) |
|
pipe = StableDiffusionXLControlNetPipeline.from_pretrained( |
|
base_model_path, |
|
controlnet=controlnet, |
|
torch_dtype=torch.float16, |
|
add_watermarker=False, |
|
vae=vae |
|
) |
|
pipe.enable_vae_tiling() |
|
|
|
|
|
target_content_blocks = BLOCKS['content'] |
|
target_style_blocks = BLOCKS['style'] |
|
controlnet_target_content_blocks = controlnet_BLOCKS['content'] |
|
controlnet_target_style_blocks = controlnet_BLOCKS['style'] |
|
|
|
csgo = CSGO(pipe, image_encoder_path, csgo_ckpt, device, num_content_tokens=4,num_style_tokens=32, |
|
target_content_blocks=target_content_blocks, target_style_blocks=target_style_blocks,controlnet_adapter=True, |
|
controlnet_target_content_blocks=controlnet_target_content_blocks, |
|
controlnet_target_style_blocks=controlnet_target_style_blocks, |
|
content_model_resampler=True, |
|
style_model_resampler=True, |
|
|
|
) |
|
|
|
style_name = 'img_1.png' |
|
content_name = 'img_0.png' |
|
style_image = Image.open("../assets/{}".format(style_name)).convert('RGB') |
|
content_image = Image.open('../assets/{}'.format(content_name)).convert('RGB') |
|
|
|
caption ='a small house with a sheep statue on top of it' |
|
|
|
num_sample=4 |
|
|
|
#image-driven style transfer |
|
images = csgo.generate(pil_content_image= content_image, pil_style_image=style_image, |
|
prompt=caption, |
|
negative_prompt= "text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry", |
|
content_scale=1.0, |
|
style_scale=1.0, |
|
guidance_scale=10, |
|
num_images_per_prompt=num_sample, |
|
num_samples=1, |
|
num_inference_steps=50, |
|
seed=42, |
|
image=content_image.convert('RGB'), |
|
controlnet_conditioning_scale=0.6, |
|
) |
|
|
|
#text editing-driven stylized synthesis |
|
caption='a small house' |
|
images = csgo.generate(pil_content_image= content_image, pil_style_image=style_image, |
|
prompt=caption, |
|
negative_prompt= "text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry", |
|
content_scale=1.0, |
|
style_scale=1.0, |
|
guidance_scale=10, |
|
num_images_per_prompt=num_sample, |
|
num_samples=1, |
|
num_inference_steps=50, |
|
seed=42, |
|
image=content_image.convert('RGB'), |
|
controlnet_conditioning_scale=0.4, |
|
) |
|
|
|
#text-driven stylized synthesis |
|
caption='a cat' |
|
#If the content image still interferes with the generated results, set the content image to an empty image. |
|
# content_image =Image.fromarray(np.zeros((content_image.size[0],content_image.size[1], 3), dtype=np.uint8)).convert('RGB') |
|
|
|
images = csgo.generate(pil_content_image= content_image, pil_style_image=style_image, |
|
prompt=caption, |
|
negative_prompt= "text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry", |
|
content_scale=1.0, |
|
style_scale=1.0, |
|
guidance_scale=10, |
|
num_images_per_prompt=num_sample, |
|
num_samples=1, |
|
num_inference_steps=50, |
|
seed=42, |
|
image=content_image.convert('RGB'), |
|
controlnet_conditioning_scale=0.01, |
|
) |
|
``` |
|
|
|
## Demos |
|
<p align="center"> |
|
<br> |
|
🔥 For more results, visit our <a href="https://csgo-gen.github.io"><strong>homepage</strong></a> 🔥 |
|
</p> |
|
|
|
### Content-Style Composition |
|
<p align="center"> |
|
<img src="assets/page1.png"> |
|
</p> |
|
|
|
<p align="center"> |
|
<img src="assets/page4.png"> |
|
</p> |
|
|
|
### Cycle Translation |
|
<p align="center"> |
|
<img src="assets/page8.png"> |
|
</p> |
|
|
|
### Text-Driven Style Synthesis |
|
<p align="center"> |
|
<img src="assets/page10.png"> |
|
</p> |
|
|
|
### Text Editing-Driven Style Synthesis |
|
<p align="center"> |
|
<img src="assets/page11.jpg"> |
|
</p> |
|
|
|
## Star History |
|
[](https://star-history.com/#instantX-research/CSGO&Date) |
|
|
|
|
|
|
|
## Acknowledgements |
|
This project is developed by InstantX Team, all copyright reserved. |
|
|
|
## Citation 💖 |
|
If you find CSGO useful for your research, welcome to 🌟 this repo and cite our work using the following BibTeX: |
|
```bibtex |
|
@article{xing2024csgo, |
|
title={CSGO: Content-Style Composition in Text-to-Image Generation}, |
|
author={Peng Xing and Haofan Wang and Yanpeng Sun and Qixun Wang and Xu Bai and Hao Ai and Renyuan Huang and Zechao Li}, |
|
year={2024}, |
|
journal = {arXiv 2408.16766}, |
|
} |
|
``` |
