This is my first distributed workflow for ComfyUI.I had a simple idea to "re-image an existing image" type request. The idea was born, and this is it executed. In a nutshell this workflow take an image you give it, runs it through a image to text model, then re-combines what the image to text generates back into a prompt with T5xxl and ClipL along with any LoRa's or CSV Styles you want.I have given some example pictures I am using the Flux GGUF models for this workflow but with a little editing you could alter it to fit any model.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/013cd275-20cf-4da9-b00a-5f8c6b1f8411/width=525/013cd275-20cf-4da9-b00a-5f8c6b1f8411.jpeg" />Some examples of what it will do. To the left the image directly from the internet. To the right, what the model did to "re-imagine" the that image.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/475be791-c943-46b2-8109-df2f51569687/width=525/475be791-c943-46b2-8109-df2f51569687.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4e10d802-2def-4ac4-a7d6-66b3406dca81/width=525/4e10d802-2def-4ac4-a7d6-66b3406dca81.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d5f201c4-69cf-4e05-8e7b-6c6a952d0506/width=525/d5f201c4-69cf-4e05-8e7b-6c6a952d0506.jpeg" />

ComfyUI - Re-imagine Image Workflow

Full version, has two Image to Text Florence models, ClipL and T5xxl models to help translate the text. This one uses the most amount of VRAM, but can still fit in my 16GB card.

Files with SHA256: 78819efbfad4d50684c78b3e809afd8d546b5f021dab6075469afe8d1ec94ab0