Workflow : image scrubbing (Patreon)

The workflow is for level-2/level-3 supporters

Type : FLUX.2-Klein

Need LORA : High resolution

Function:

Start with a reference image, inherit its content and elements, then generate countless realistic images ( as many as you want )

Guide :

The full view of the workflow

It contains three major sections: prompt inversion, image redrawing, and upscaling and restoration.

The green area is for reverse-inferring prompts, which is designed to improve the accuracy of redrawing. If high precision is not required, you can disable prompt reverse inference for faster running speed.

The red area is used for image redrawing, and this area adopts a LoRA model named ZIT_fdpo. It can enhance contrast, and whether to enable it depends on your actual situation.

The purple area is an enlarged restoration, using my "High resolution" LORA, which can maximize the consistency between the enlarged image and the original one. Below is an example:

X5h7Jq7qgSY6i4lpgylkrQ

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

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

Disclaimer: The model or workflow is experimental and intended for learning and communication purposes only. Do not use it for any commercial activities.Users bear full responsibility for the generated content, including its legality, ethical implications, or potential misuse.By using this model or workflow, you are deemed to have agreed to these principles. Please use it responsibly within the scope permitted by local laws.