# OmniGen-ComfyUI
**Repository Path**: analyzesystem/OmniGen-ComfyUI
## Basic Information
- **Project Name**: OmniGen-ComfyUI
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 1
- **Forks**: 0
- **Created**: 2024-11-04
- **Last Updated**: 2024-11-13
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# OmniGen-ComfyUI
a custom node for [OmniGen](https://github.com/VectorSpaceLab/OmniGen), you can find [workflow here](./doc/)
## EXample
in prompt text, you only need `image_1`, text will auto be `
<|image_1|>`
|text|image_1|image_2|image_3|out_img|
|--|--|--|--|--|
|`A curly-haired man in a red shirt is drinking tea.`|--|--|--||
|`The woman in image_1 waves her hand happily in the crowd`||--|--||
## Tips
For out of memory or time cost, you can refer to [inference.md#requiremented-resources](https://github.com/VectorSpaceLab/OmniGen/blob/main/docs/inference.md#requiremented-resources) to select a appropriate setting.
```
{"task_type":"text_to_iamge","instruction":"A white cat resting on a picnic table.","input_images":[],"output_image":"cat.png"}
{"task_type":"image_edit","instruction":"
<|image_1|> The umbrella should be red.","input_images":["edit_source_1.png"],"output_image":"edit_target_1.png"}
{"task_type":"segementation","instruction":"Find lamp in the picture
<|image_1|> and color them blue.","input_images":["seg_input.png"],"output_image":"seg_output.png"}
{"task_type":"try-on","instruction":"
<|image_1|> wears
<|image_2|>.","input_images":["model.png","clothes.png"],"output_image":"try_on.png"}
{"task_type":"pose", "instruction": "Detect the skeleton of human in
<|image_1|>", "input_images": ["human_pose.png"], "output_image": "pose.png"}
```