Answers ( 1 )

    0
    2025-04-01T01:52:56+00:00

    The tool requires two inputs:
    1. **Source Image**: Extracts Canny edges as structural guidance.
    2. **Text Prompt**: Describes desired output content.
    The model then generates a new image that adheres to the extracted edges while incorporating elements from the text prompt. This dual-input approach allows controlled generation where composition remains faithful to the original structure.

Leave an answer