This is my personal basic workflow for F3K single-image editing. completely free of charge. You need to install the custom nodes I developed to use it. The link is below

https://github.com/no8d/ComfyUI-NO8D-controls

Applicable to all F3K editing LoRAs released by me

✨MoreReal for F3K✨private version

Now, let's take a look at the full workflow. Here it is.

The lower part is for the puzzle function and can be deleted if not needed.

The main functional area is divided into 3 parts.

It is the image library, used to load the images you want to edit. Many editing models impose certain restrictions on the side lengths of input images to maximize alignment between input and output images. The menu in the red box serves this purpose. It crops the selected image to the closest standard aspect ratio, which is 3:4 in this example, and ensures the side lengths are multiples of 8, 16, 32 or 64. These are common multiple constraints. As shown in the example, the output image has a 3:4 aspect ratio and side lengths that are multiples of 32. Select the first option if you do not wish to use this feature.

此处为工作流的核心工作区，你可以设置LoRA和权重，并设置最终输出的尺寸，默认为 《MoreReal for F3K》（你可以改成任意单图编辑的LoRA），权重=0.9，输出的尺寸=两百万像素。下方的节点可以选择随机种子。

打开子图你会看到一套标准的F3K的单图编辑工作流

唯一需要注意的是，由于该工作流使用的是int8的基础模型，所以ksample设置的是16步，如果你使用base版的基础模型，需要将16步改为50步。

OK! That's all! I hope you like it!

If you like my sharing and want to get more content and resources related to AI image generation, welcome to join my private community.👇👇👇

NO8D-AI-Workshop

🫡May the AI-power be with you, see you soon!🫡

Disclaimer: My model or workflow is solely for learning and communication purposes and shall not be used for any commercial activities. All responsibilities for the generated content, including its legality, ethical implications, or potential misuse, are borne entirely by the user. By using this model or workflow, you agree to this principle. Please use it responsibly within the scope of local laws.