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.
ComfyUI-OmniGen - A ComfyUI custom node implementation of OmniGen, a powerful text-to-image generation and editing model.
| Date | Stars |
|---|---|
| 2026-07-31 | 300 |
| 2026-08-04 | 300 |
| 2026-08-06 | 300 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# ComfyUI-OmniGen
A ComfyUI custom node implementation of OmniGen, a powerful all in one text-to-image generation and editing model.
$${\color{red}If\ this\ custom\ node\ helps\ you\ or\ you\ like\ my\ work,\ please\ give\ me⭐on\ this\ repo!}$$
$${\color{red}It's\ a\ greatest\ encouragement\ for\ my\ efforts!}$$
## Updates
- 2025/01/22: Added new features and bug fixes. Refer to [update.md](UPDATE.md) for details.
- 2024/11/11: Added new features and bug fixes. Refer to [update.md](UPDATE.md) for details.
<details>
<summary><h2>Features</h2></summary>
- Text-to-Image Generation
- Image Editing
- Support for Multiple Input Images
- Memory Optimization Options
- Flexible Image Size Control
</details>
## Installation
#### 1. ComfyUI-Manager
1. Search for `ComfyUI-OmniGen` on [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) and install it.
2. Restart ComfyUI
#### 2. Git Clone
1. Open the terminal on the ComfyUI `ComfyUI/custom_nodes` folder
2. Run `git clone https://github.com/1038lab/ComfyUI-OmniGen.git`
3. Restart ComfyUI
## Install the required Python packages:
1. Open the terminal on the `ComfyUI/custom_nodes/ComfyUI-OmniGen` folder
2. `..\..\..\python_embeded\python.exe -m pip install -r requirements.txt`
<details>
<summary><h3>Auto-Download Feature</h3></summary>
The node includes automatic downloading of:
1. OmniGen code from GitHub repository
2. Model weights from Hugging Face
No manual file downloading is required. The node will handle everything automatically on first use.</details>
>[!IMPORTANT]
>The first time you use this custom node, it will automatically download the model from Hugging Face. Please be patient, as the download size is approximately 15.5 GB, and it may take some time to complete.
>
>Alternatively, you can manually download the model from Hugging Face at the following link:
>Download OmniGen-v1 from [Hugging Face](https://huggingface.co/Shitao/OmniGen-v1/tree/main)
>After downloading, place the model in the following directory: `comfyui/models/LLM/OmniGen-v1`
### Example workflows
Simple usage for text to image & image to image. [workflow](/Examples/omnigen_t2i_i2i.json)
Generate an image that combines 2 images. [Workflow](/Examples/omnigen_combine.json)
Following the pose of this image `image_1`, generate a new photo: An viking old man standing.
Generate a depth map from the input image and create a new image based on the depth map. [Workflow](/Examples/depthmap2image.json)
Deblur this image. `image_1`
### Example prompts:
| Prompt | Image_1 | Image_2 | Image_3 | Output |
| ------ | ------ | ------ | ------ | ------ |
| 20yo woman looking at viewer | | | |  |
| Transform `image_1` into an oil painting |  | | |  |
| Transform `image_2` into an Anime |  | | |  |
| The girl in `image_1` sitting on rock on top of the mountain. |  | | |  |
| Combine `image_1` and `image_2` in anime style. |  |  | |  |
| A woman from `image_1` and a man from `image_2` are sitting across from each other at a cozy coffee shop, each holding a cup of coffee and engaging in conversation. |  |  | |  |
| FolExcerpt of 6,582 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:cc06a62262cc48b0, desc:text-to-image, desc:image generation