Are you sure the pipeline works that way? I know what you mean and it would seem like a huge oversight on their part to apply the denoise before the other edits. I would assume that increasing exposure, for example, would ignore the applied denoise rather than apply it overtop? If that wording makes any sense
Regardless I’ve used it to rescue photos I’ve taken on a nexus 4 over a decade ago, making them look like proper photos, and I find the feature so useful that it’s irreplaceable to me
The other feature is the AI content aware fill. In darktable, can you circle a piece of garbage on the ground and effortlessly remove it? Or do you have to do some manual clone stamping etc etc?
In a recent instance, a friend requested an album cover from a 3x2 image that I needed to expand to be 1x1. Can you tell that the left and right edges of this are not real? I don’t think I would have been skilled enough to pull this off without AI tools. https://f4.bcbits.com/img/a1356058193_10.jpg
Please understand me correctly: Machine learning does have its use as an image editing. but not in raw development. Sure, VFX are fine, but the goal of raw development is to make the files that the camera has put out look as good as possible. And for that, machine learning is inadequate, because again, hallucinations and other defects. Once you have processed your image with the raw development software, sure. Machine learning, denoising, expansion and other VFX will certainly work. But my recommendation is to keep it out of raw development, not for purist reasons, but because there’s genuinely no reason to use it, as we need to get precise results from raw first, and then we can add our VFX on top of that.
About the raw pipeline of Darktable, this is one of its greatest features. You can freely reconfigure it to suit your needs. By default, it uses a scene-referred workflow and you should really stick with that. But if you’re an advanced user, you can freely shuffle the modules around as you like, just like you can do in DaVinci Resolve.
Edit: For beginners, really stick with the modules that you’ll find in the different headers. Also, manipulate your modules starting from bottom to top, as this is the processing order for the modules.
I will try it based on your second paragraph.
Are you sure the pipeline works that way? I know what you mean and it would seem like a huge oversight on their part to apply the denoise before the other edits. I would assume that increasing exposure, for example, would ignore the applied denoise rather than apply it overtop? If that wording makes any sense
Regardless I’ve used it to rescue photos I’ve taken on a nexus 4 over a decade ago, making them look like proper photos, and I find the feature so useful that it’s irreplaceable to me
The other feature is the AI content aware fill. In darktable, can you circle a piece of garbage on the ground and effortlessly remove it? Or do you have to do some manual clone stamping etc etc?
In a recent instance, a friend requested an album cover from a 3x2 image that I needed to expand to be 1x1. Can you tell that the left and right edges of this are not real? I don’t think I would have been skilled enough to pull this off without AI tools. https://f4.bcbits.com/img/a1356058193_10.jpg
Please understand me correctly: Machine learning does have its use as an image editing. but not in raw development. Sure, VFX are fine, but the goal of raw development is to make the files that the camera has put out look as good as possible. And for that, machine learning is inadequate, because again, hallucinations and other defects. Once you have processed your image with the raw development software, sure. Machine learning, denoising, expansion and other VFX will certainly work. But my recommendation is to keep it out of raw development, not for purist reasons, but because there’s genuinely no reason to use it, as we need to get precise results from raw first, and then we can add our VFX on top of that.
About the raw pipeline of Darktable, this is one of its greatest features. You can freely reconfigure it to suit your needs. By default, it uses a scene-referred workflow and you should really stick with that. But if you’re an advanced user, you can freely shuffle the modules around as you like, just like you can do in DaVinci Resolve.
Edit: For beginners, really stick with the modules that you’ll find in the different headers. Also, manipulate your modules starting from bottom to top, as this is the processing order for the modules.