It’s here to stay whether we like it or not A good image processor will know and understand how to use masks to control what’s happening to their images, and will apply the effects of the tool in a way that doesn’t lead to misinterpretation of the image data that was captured. I expect we’ll see a lot more AI based features added to software processing tools over the coming months to year. There’s currently an AI web based tool called Star Fixer that can correct your stars for tilt or coma. Photoshop already incorporates AI like features with it’s content aware fill functions. And pretty soon other software will follow. They might not even explicitly state the features are AI based. My basic processing routine and some examples showing how to use Topaz AI But we can be sure to see more of this stuff in the future. After removing any light pollution and cropping out the edges from dithering, I typically do a masked stretch with the default values. You have to use a small preview window over an area that you know is pure black. This gets the stars to the perfect value (if you've not overexposed, this makes your brightest stars become white right at the center point. I then duplicate the image (whether it's a single channel like HA, or the RGB image). I make a duplicate image here because the StarNet process is destructive, and I sometimes want to go back to the original image before StarNet. On the duplicate image I run StarNet to remove the stars and make sure it has the star mask button is checked. One that is only stars, and one that is only background with nebulosity. I then right click on the gray tab of the image and select Identify, and give it a name. Stars for the star image, and starless for the starless image.
0 kommentar(er)
