Introduction
This workflow converts cityscape images into stunning yarn-style artwork, mimicking the texture of woven threads. Perfect for adding a handcrafted touch to your visuals. Just upload a city image and get a unique, cozy masterpiece!
Florence2
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages our FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model's sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model.
Read more:https://github.com/kijai/ComfyUI-Florence2
Download:https://github.com/kijai/ComfyUI-Florence2.git
Workflow overview
How to use this workflow?
Step 1: Upload Image and Generate Prompt
First, you need to upload an image. Then, the Florence2 can automatically generate a prompt that matches the content of the image.
Step 2: Scribble & Depth
Scribble provides the structural framework, while Depth enhances the sense of three-dimensionality and spatial dimensions. Together, they ensure that the generated yarn-style images have clear outlines and effectively convey depth and layers, making the artwork more vivid and engaging.
Step 3: Output
In this workflow, we have preloaded two LoRA models to help generate yarn-style city photos. Have a try!
