Skip steps for input image

Added the stable diffusion skip steps sampler, as this can be more helpful for creating animations.

Skip start: 

• Skips a proportion of the start of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in less influence from the init_image, while higher values will result in more influence from the input image. (e.g. a value of 1 would return 50% of your init_image, where a value of 1 would return you almost the same image.)

Skip end

• Skips a proportion of the end of the diffusion steps, allowing the init_image to influence the final generated image. Lower values will result in less influence from the init_image, while higher values will result in more influence from the input image. (e.g. a value of 1 would return 50% of your init_image, where a value of 1 would return you almost the same image.)

Reduced text size overall in the app