ComfyUI
Last updated
Last updated
ComfyUI: The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. Now you can use it in dify, input the prompt or images, and get the generated image.
Please refer to its official documentation to ensure that ComfyUI can run normally and generate images.
If you don't need dify to pass in the prompt, you can skip this step. If your prompt node is connected to the only KSampler node in ComfyUI, you can skip this step.
Otherwise, use the string {{positive_prompt}} to replace the positive prompt content, and {{negative_prompt}} to replace the negative prompt content.
As shown in the figure, select `Save(API Format)`, if there is no such selection, you need to enable `Dev Mode` in the settings.
Fill in the access address in Tools > ComfyUI > Go to Authentication, if you are using a docker deployment of Dify, this address is usually http://host.docker.internal:8188.
Open its Workflow tool, fill in the content in the API file you just exported in WORKFLOW JSON, and you can generate normally.
Some ComfyUI workflows require multiple images inputs. In dify, it will find every LoadImage node in the WORKFLOW JSON and fill in the image files input by the user in order. When you want to change this order, you can adjust it by filling in the Image node ID list. For example, if your workflow needs to input images into the 35th, 69th, and 87th nodes, then input 69,35,87 will pass the first image to the 69th node.
