66 lines
3.2 KiB
Markdown
66 lines
3.2 KiB
Markdown
# 🎨 Object Fusion Pipeline
|
||
|
||
## 🌟 Motivation
|
||
Have you ever fantasized about crafting a single masterpiece from elements of different photos? 😲 What if I told you that manually prompting each object's shape, color, and features for diffusion could be a thing of the past? And let’s be real, using GPT to describe each object step by step can feel like chasing an AI in slow motion. 🐢💤
|
||
|
||
Here, I introduce a complete pipeline that takes two images as input, allowing you to choose which objects from the images you want to fuse seamlessly.
|
||
|
||
## 🚀 Features
|
||
- Combine objects from two different images into a single scene.
|
||
- Easy selection and customization of objects to be fused.
|
||
- Optimized integration with ComfyUI.
|
||
|
||
## 🖼️ Some Examples
|
||
|
||
|
||
|
||
<details>
|
||
<summary>Click to expand/collapse</summary>
|
||
|
||
|
||
|
||
|
||
|
||
</details>
|
||
|
||
## 🛠️ Installation
|
||
|
||
1. Clone this repo into the `custom_nodes` directory in [ComfyUI](https://github.com/comfyanonymous/ComfyUI):
|
||
```bash
|
||
git clone https://github.com/ducido/ObjectFusion_ComfyUI_nodes
|
||
```
|
||
|
||
3. Clone these amazing repositories and follow their instructions:
|
||
- [ComfyUI-SD3-nodes](https://github.com/liusida/ComfyUI-SD3-nodes)
|
||
_Note: Place the 3 clips model into `models/clip`._
|
||
- [ComfyUI-Custom-Scripts](https://github.com/pythongosssss/ComfyUI-Custom-Scripts)
|
||
- [img2txt-comfyui-nodes](https://github.com/christian-byrne/img2txt-comfyui-nodes)
|
||
|
||
4. Install the required packages:
|
||
```bash
|
||
conda create -n objectfusion python=3.10 -y
|
||
conda activate objectfusion
|
||
pip install -r custom_nodes/ObjectFusion_ComfyUI_nodes/requirements.txt
|
||
wget https://huggingface.co/camenduru/YoloWorld-EfficientSAM/resolve/main/efficient_sam_s_gpu.jit -P custom_nodes/ObjectFusion_ComfyUI_nodes/Custom_ComfyUI_YoloWorld_EfficientSAM
|
||
```
|
||
5. Or you can install with [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager) which is much easier and faster.
|
||
|
||
## 📌 Note
|
||
_All the folders, except `CROP_OBJECT`, are from other repositories. Thank you for your amazing works, I appreciate that. Besides, I have made some minor modifications to fit this project. Here are the details:_
|
||
|
||
- **[Custom_ComfyUI-YoloWorld-EfficientSAM](https://github.com/ZHO-ZHO-ZHO/ComfyUI-YoloWorld-EfficientSAM)**
|
||
- Added 2 output fields: `BBOX`, `categories`.
|
||
- Displayed ID also in the IMAGE output (e.g., `{ID} - {class} - {confidence}`).
|
||
|
||
- **[comfyui-llm-assistant](https://github.com/longgui0318/comfyui-llm-assistant)**
|
||
- Removed input field: `prompt`.
|
||
- Added 4 input fields: `object1`, `desc_obj1`, `object2`, `desc_obj2`.
|
||
- Change all `default` value to `""` because the newest frontend of ComfyUI consider `None` value as a bug
|
||
|
||
|
||
## 🤝 Contributing
|
||
Contributions are welcome! Please open an issue or submit a pull request.
|
||
|
||
## 📄 License
|
||
This project is licensed under the MIT License.
|