designart

AI Tools for the userThis articles focuses on AI tools from the perspective of a person who uses them, creating AI tools is a different subject that deserves its own article.Definition and PurposeAI tools simplify complex tasks like image or video generation, enabling users to achieve results with minimal effort. Some tools offer user-friendly interfaces, like forms or clickable options, to generate content based on prompts or uploaded images. You can think of them as handy presets, or a simple specific use appliance that does one thing as opposed to a general use appliance. When using the standard way of creating AI art you have to personally select a model, a combination of LORAs and their respective strengths, the type of sampler, the number of steps, you have to write a full positive and a full negative prompt, not to mention a number of other settings if you want to make the most of your tokens. With an AI tool most of this has been or at least can be already taken care of by someone who (hopefully) knows how to achieve the intended result. This leaves you to focus solely on your creative idea without having to delve into the technical aspects if that's not something you're interested in.This naturally means that any single AI tool will have a limited scope as it will be made to produce a specific result, but with so many users contributing their own AI tools, it's just a matter of finding the one that fits your needs. Some AI tools provide lots of options to choose from, others only the most essential ones. The former are more flexible, the latter generally have a more predictable result.But there's more to AI tools than just simplifying the process of AI art. Since the creation of AI tools is only limited by someone's imagination, it is possible to create AI tools with abilities not accessible through the standard forms. With an AI tool it is for example possible to use one type of model for the initial image generation and then use a different type of model for detailing. This can be very handy since different models have different strengths and weaknesses.Advice for usageBrowse through the AI tools section to get a feeling for what's available in that realm. Evaluate the AI tool before using it by checking other people's posts made with it. This can tell you what the AI tool is good at and what you can expect from it. AI tools vary greatly in terms of complexity and quality, so the costs aren't uniform either, but can vary quite substantially. Realize that a tool with a higher cost can still be worth it, if it more consistently produces high quality output. No matter which AI tool you use to generate something, the result will come up in your standard creation flow even if you leave or close the AI tool's page while it is still working. There is currently a discount active on all AI tools so take advantage of it to save on tokens.

This is an article aimed at everyone who would like to get the most of what LoRAs have to offer. They can be very strong and can play a big role in how your image turns out, so it pays off to choose them carefully. Not only because they can actually make your picture worse, but also because you have a limited number of LoRAs you can use at the same time and so you don't want to waste those slots.As far as I'm concerned you can divide LoRAs intro three main groups - good, bad and unnecessary. Good ones help you make better images, bad ones hurt them, while the unnecessary ones don't hurt the picture, but you can achieve the same effect without them so they just waste a LoRA slot. The bad ones tend to be easy to spot because they hurt the generated image either by lowering the general quality, introducing artifacts or simply not delivering what they promise. To correctly identify the good and unnecessary ones however you need to conduct a controlled test, or you could mistakenly attribute the effects of the model, prompt, a different concurrently used LoRA, or even just a different seed to the LoRA in question and not realize what is your LoRA's actual contribution.So how do you properly test a LoRA? The same way you test anything, which is to isolate it. In our case this means running two generations where you only change a single thing. You fix the seed (don't leave it random!), you don't change the prompt, sampler, steps, cfg scale, or indeed anything at all and run the exact same generation twice, once with and once without the LoRA. Now you have two pictures to compare and you can be sure that the difference between them was actually caused by the tested LoRA, which lets you confidently determine if the LoRA worth using or not.Some LoRAs use a trigger that you add to the prompt and since this obviously changes the prompt and thus changes a second variable, this case needs a bit more attention. Lets say we're testing a LoRA about Halloween and its trigger word is also "Halloween". Your chosen model/checkpoint very likely already understands this famous holiday and so adding this word to the prompt will bring a Halloween note even without using the LoRA. This means you either test the LoRA without using the trigger, but since this usually lowers its effect, you can also test by adding the trigger to your prompt even in your run without the LoRA to ensure that the prompt remains unchanged. We want to see the real effect of the LoRA, not the effect of having "Halloween" in the prompt.If you start testing LoRAs this way, I think you might be surprised by how many of them don't add much value to your pictures and that some even make them worse. You can check my posts where I have been documenting my tests of skin LoRAs, always posting the "original" generation alongside the one with a LoRA active so you can easily compare. There you can even see how one of the most run Flux LoRAs appears to not work at all and doesn't change a single pixel. Wouldn't you rather run LoRAs that improve your pictures? I'm sure you would, but to do that you have to know what the LoRA actually does.