One of the things is, I cannot draw art, and I am in fact terrible at it.
But I have an idea, so I describe the strange idea to A.I, and then it draws it out, sometimes it takes its liberties as long as it exists or its seen it before, and what comes out can be very creative. Having said that, I am aware that it is nowhere as competent as a human, all the walking animations all gone wrong for spritesheets, it can only generate mostly concept arts or stills and even then, the eye expressions are always off or like dead fish
It also ignores instructions. It's not that I don't want to pay for a team to do my game or rp, more like I can't afford to without going all in and bankrupt if the project tanks.
When it generates right, you get really happy, but most of the time, it trips over itself and u get frustrated prompting it again and again XD.
Some of you might say, "learn to draw". My reply to that is, u think I didn't try? Man people laughed at my drawings, or how fat and out of shape sonic was when I did it. I copied pokemon from the pics, and everyone laughed man when I kept those pictures and manga in a special folder though they looked like crap.
Viewing post in Does AI Hatred Hurts Artists? My Experience...
Try interacting with it like this:
Don't focus on instructing it, necessarily. Instead, give it a vibe or a feeling. You aren't telling it what to do, like most think, you are seeding the bloom. Every message, every image generation, it's a totally new AI starting from scratch. A chat bot has the luxury of reading your chat log whenever it replies. An image/video generator, though... you gotta understand how to store data in language by using speaking with resonance.
Normal Example:
"a girl standing in a field, her hair is blowing in the wind, there are flowers in the field"
Resonant Example:
"the way she stood against the wind, her hair like silk in the summer sun... the flowers were gently swaying in the breeze as the clouds drifted lazily overhead..."
You should notice a dramatic increase in quality, but each AI model is different so you gotta play around with it. There's a lot going on in the background and it's about way more than the words you type. It's even about the words you don't type. Synonyms are common phrases are your best friends. Beware data redundancies by using the same words too often in one prompt. Rather than using the same word twice, swap a synonym. But be aware of the cultural context related to each word.
Sometimes (For not saying all the times) text instructions are no enough for the AI to 'understand' what you want to do. I use Krita AI Diffusion to draw by hand a base sketch in Krita and then iterate bit by bit with SD (Stable Diffusion) or SDXL over it like a filter. Perhaps if you already have some experience hand drawing it could help you: https://kritaaidiffusion.com/
Or this one. But is more limited: https://www.artbreeder.com/tools/collage
I am not trying to do advertisement haha, i just though this could help you since you mentioned you already draw.