Wan2.1 Text to Image

详情

下载文件 (1)

模型描述

Description

This workflow allows you to create fantastic images with minimum effort. It utilizes Ollama to enhance and refine your prompts. You can use a few keywords and topics and Ollama will do the rest.

I recommend using gemma3:latest as it is uncensored and lightweight.

The results are spectacular and, in my opinion, much better then Flux can do.

How to use it?

Simply drag downloaded file (unzip it first) to ComfyUI canvas. More instructions inside the workflow.

此模型生成的图像