86 lines
3.5 KiB
Markdown
86 lines
3.5 KiB
Markdown
# ComfyUI-Fluxtapoz
|
|
|
|
A set of nodes for editing images using Flux in ComfyUI
|
|
|
|
## Examples
|
|
|
|
See `example_workflows` directory for examples.
|
|
|
|
No ControlNets are used in any of the following examples.
|
|
|
|
## Rectified Flow Inversion (Unsampling from [RF Inversion](https://rf-inversion.github.io/))
|
|
|
|
Admittedly this has some small differences between the example images in the paper, but it's very close. Will be updating as I find the issue.
|
|
It's currently my recommended way to unsample an image for editing or style transfer.
|
|
|
|
Use [this workflow](https://github.com/logtd/ComfyUI-Fluxtapoz/blob/main/example_workflows/example_rf_inversion_updated.json) for RF-Inversion.
|
|
|
|
|
|
|
|
### RF-Inversion Stylization
|
|
|
|
RF-Inversion can also be used to stylize images.
|
|
|
|
Use [this workflow](https://github.com/logtd/ComfyUI-Fluxtapoz/blob/main/example_workflows/example_rf_inversion_stylization.json) to style images.
|
|
|
|
|
|
|
|
|
|
## RF-Edit (Unsampling from [RF-Solver-Edit](https://github.com/wangjiangshan0725/RF-Solver-Edit))
|
|
RF-Edit is an alternative way to edit images. It may suit some use cases better than RF-Inversion and I recommend trying both.
|
|
|
|
Use [this workflow](https://github.com/logtd/ComfyUI-Fluxtapoz/blob/main/example_workflows/example_rf_edit_workflow_alternative.json) for RF-Edit.
|
|
|
|
|
|
|
|
|
|
|
|
## Regional Prompting
|
|
Regional prompting allows you to prompt specific areas of the latent to give more control. You can combine it with Redux, but Redux is so powerful it dominates the generation.
|
|
This implementation is based on [InstantX Regional Prompting](https://github.com/instantX-research/Regional-Prompting-FLUX).
|
|
|
|
Use [this workflow](https://github.com/logtd/ComfyUI-Fluxtapoz/blob/main/example_workflows/example_flux_regional.json) for regional prompting.
|
|
|
|
|
|
|
|
|
|
## Enhancement
|
|
There are two nodes for Perturbed Attention Guidance (PAG) and Smoothed Energy Guidance (SEG) that can add detail to images.
|
|
|
|
The following from left to right: Vanilla Flux, PAG, SEG
|
|
|
|
|
|
|
|
|
|
## Acknowledgements
|
|
|
|
[RF-Inversion](https://rf-inversion.github.io/)
|
|
|
|
```
|
|
@article{rout2024rfinversion,
|
|
title={Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations},
|
|
author={Litu Rout and Yujia Chen and Nataniel Ruiz and Constantine Caramanis and Sanjay Shakkottai and Wen-Sheng Chu},
|
|
journal={arXiv preprint arXiv:2410.10792},
|
|
year={2024}
|
|
}
|
|
```
|
|
|
|
[RF-Solver-Edit](https://github.com/wangjiangshan0725/RF-Solver-Edit)
|
|
```
|
|
@article{wang2024taming,
|
|
title={Taming Rectified Flow for Inversion and Editing},
|
|
author={Wang, Jiangshan and Pu, Junfu and Qi, Zhongang and Guo, Jiayi and Ma, Yue and Huang, Nisha and Chen, Yuxin and Li, Xiu and Shan, Ying},
|
|
journal={arXiv preprint arXiv:2411.04746},
|
|
year={2024}
|
|
}
|
|
```
|
|
[InstantX Regional Prompting](https://github.com/instantX-research/Regional-Prompting-FLUX)
|
|
```
|
|
@article{chen2024training,
|
|
title={Training-free Regional Prompting for Diffusion Transformers},
|
|
author={Chen, Anthony and Xu, Jianjin and Zheng, Wenzhao and Dai, Gaole and Wang, Yida and Zhang, Renrui and Wang, Haofan and Zhang, Shanghang},
|
|
journal={arXiv preprint arXiv:2411.02395},
|
|
year={2024}
|
|
}
|
|
```
|