ComfyUI-APISR-KJ

ComfyUI-APISR-KJ
★ 77

APISR集成图像放大超分辨率ComfyUI扩展
在 ComfyUI 中调用 APISR 模型进行图像放大与超分辨率处理,便捷集成高质量 upscaling 模型。
💡 为生成图片做高质量放大与细节增强。
🍴 6 Forks💻 Python🔄 2024-05-21
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/b45acaa3411d
📦 requirements.txt
numpy
scipy
omegaconf
timm>=0.9.7
image
📄 README

Node to use APISR upscale models in ComfyUI

Original repository:

https://github.com/Kiteretsu77/APISR

:european_castle: Model Zoo

  • For Paper weight
  • For Diverse Upscaler
  • For Paper Weight

    | Models | Scale | Description |

    | ——————————————————————————————————————————- | :—- | :——————————————- |

    | 4x_APISR_GRL_GAN_generator | 4X | 4X GRL model used in the paper |

    For Diverse Upscaler

    Actually, I am not that much like GRL. Though they can have the smallest param size with higher numerical results, they are not very memory efficient and the processing speed is slow for Transformer model. One more concern come from the TensorRT deployment, where Transformer architecture is hard to be adapted (needless to say for a modified version of Transformer like GRL).

    Thus, for other weights, I will not train a GRL network and also real-world SR of GRL only supports 4x.

    | Models | Scale | Description |

    | ——————————————————————————————————————————- | :—- | :——————————————- |

    | 2x_APISR_RRDB_GAN_generator | 2X | 2X upscaler by RRDB-6blocks |