Back
Selfie + Text Prompt to Studio Photoshoot Doodle

This ComfyUI workflow, titled 'Selfie + Text Prompt to Studio Photoshoot Doodle,' is designed to transform a simple selfie into a series of fashion editorial photographs enhanced with playful doodle illustrations. By leveraging a combination of advanced AI models such as Google Gemini Image and Nano Banana Pro, this workflow allows users to creatively visualize their outfits in a studio photoshoot setting. The process begins with uploading a selfie and providing a descriptive text prompt about the desired outfit. The workflow then generates four distinct fashion images, each adorned with unique doodles.

Technically, this workflow utilizes a series of nodes to achieve its artistic transformation. The LoadImage node is responsible for importing the user's selfie, while the PrimitiveStringMultiline node captures the text prompt. The GeminiImage2Node plays a crucial role in generating the initial set of images based on the input data. Users can then select their preferred image for further enhancement using the batch_index parameter, which is managed by the ImageBatch node. Finally, the selected image is upscaled and refined with additional face detail restoration, ensuring high-quality output suitable for fashion editorial purposes. This workflow is particularly useful for fashion designers, photographers, and social media influencers looking to create visually striking content with minimal effort.