Introduction
By leveraging Calvton-Flux's cutting-edge inpainting and try-on capabilities, the workflow enables seamless garment replacement. Whether you're designing fashion concepts, creating digital marketing visuals, or experimenting with virtual try-ons, this workflow ensures creative flexibility and professional-grade results.
Calvton-Flux
An state-of-the-art virtual try-on solution that combines the power of CATVTON (CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models) with Flux fill inpainting model for realistic and accurate clothing transfer. Also inspired by In-Context LoRA for prompt engineering.
Read more and download: https://github.com/nftblackmagic/catvton-flux.git
Workflow Overview
How to use this workflow?
Step 1: Upload Images and Apply Mask
Upload a model image to start, then use the masking tool to define the area you want to replace.
Upload a garment image.
Step 2: Adjust Input Dimensions
Resize both the base image and mask to ensure compatibility with the modelâs input requirements.
Step 3: Generate the TryOn Image
- Steps: Set the number of diffusion steps (e.g., 30) to balance quality and speed.
- Guidance Scale: Control how closely the output adheres to the mask and input prompt (e.g., 30 for high fidelity).
- Seed: Define or randomize to introduce subtle variations or ensure consistent results.
Step 4: Export the Final Image
Export the try-on image in your desired format for use in fashion design, marketing, or creative projects.
