Abstract: Techniques are described for generating custom team emblems using stable diffusion based on input text describing a desired image. A circle is overlaid in the center of a pure-color background representing each team's “color” and used as the input to stable diffusion img2img to produce emblems. This produces high-quality emblem outputs that generally match the input color.

Abstract: Techniques are described for generating images such as but not limited to custom team emblems using stable diffusion (SD) based on input text describing a desired image. A pixelated multi-color palette with an optional guidance image is input to a SD model to achieve a desired target color for an image generated in response to a short text input description. The optional guidance image may be used for more accurate output images in terms of conforming to the desired foreground object and permit the use of lower strength values.

Abstract: Techniques are described for guiding stable diffusion to produce images with a contrasting foreground/background. Po stprocessing is implemented using segmentation and chromakeying to remove the background. These techniques extract an alpha channel in generated images to force stable diffusion to generate output with a background in a specified color, which is then removed from the image in output post-processing. Present techniques leverage the img2img inpainting pipeline with a noise mask that covers the image edges, applying noise (and generating content) only in the center of the image, thereby forcing a strong background/foreground distinction.