DiffMorpher-ComfyUI

DiffMorpher-ComfyUI
★ 17

图像形变风格迁移ComfyUI集成自动权重下载
将DiffMorpher集成到ComfyUI的自定义节点，便捷运行图像形变与风格迁移的扩散流程，自动下载权重并简化工作流。
💡 在ComfyUI中快速使用DiffMorpher进行图像形变与风格迁移工作流。
🍴 2 Forks💻 Python🔄 2024-07-17
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/b6135d9bd930
📦 requirements.txt
accelerate
diffusers
einops
numpy
opencv_python
Pillow
safetensors
tqdm
transformers
lpips
📄 README

DiffMorpher-ComfyUI

a custom node for DiffMorpher,you can find base workflow in doc

Example

image_0 | image_1 | output

—– | —- | —-

How to use

# in ComfyUI/custom_nodes
git clone https://github.com/AIFSH/DiffMorpher-ComfyUI.git
cd DiffMorpher-ComfyUI
pip install -r requirements.txt

weights will be downloaded from huggingface

Tutorial

DiffMorpherNode

required

  • image__0: the first image (default: “”)
  • prompt_0: Prompt of the first image (default: “”)
  • image_1: the second image (default: “”)
  • prompt_1: Prompt of the second image (default: “”)
  • use_adain: Use AdaIN (default: False)
  • use_reschedule: Use reschedule sampling (default: False)
  • lamb: Hyperparameter $\lambda \in [0,1]$ for self-attention replacement, where a larger $\lambda$ indicates more replacements (default: 0.6)
  • save_inter: Save intermediate results (default: False) if True, frame saved in ComfyUI/output/diffmorpher
  • num_frames: Number of frames to generate (default: 16)
  • duration: Duration of each frame (default: 100)

    • optional

  • diffusers_model: Pretrained model path (default: “stabilityai/stable-diffusion-2-1-base”)
  • lora_0: Path of the lora directory of the first image (default: “”)
  • lora_1: Path of the lora directory of the second image (default: “”)

    • ask for answer as soon as you want

    wechat: aifsh_98

    need donate if you mand it,

    but please feel free to new issue for answering

    Windows环境配置太难？可以添加微信：aifsh_98，赞赏获取Windows一键包，当然你也可以提issue等待大佬为你答疑解惑。