Mudge

Writing a prompt is simple. However Avoiding Unfortunate Image Results, that can sometimes pose a challenge. To begin let’s start with some basics and a few work prompt challenges…Step 1. Chose Your ThemeWhat do you want to create? An epic fantasy battle? A snapshot of models on a runway? Pirate ships in a storm? A lush garden full of gnomes? Giant Mecha battling on an alien moon? Clowns tossing pies at each other? With AI there is virtually no limit. Sci-fi space opera, Frankenstein’s monster at the prom, anime unicorns surfing on rainbows, funny chibi characters, if you can imagine it, and describe it in a prompt, the odds are you will be able to create it. You are the artist. AI is your brush.Let’s say you want “vintage” Hollywood style pics. Very simple to do with the right model, right? Sure. But you can often achieve similar results with a good prompt.You knew that? Of course you did. But what adjectives you might like to use for a really retro Hollywood style will depend upon the genre. For instance to describe Film Noir words like: pulp, sultry, brooding, sensual, dark, shadowy, steamy, &tc may leap to mind. Those same adjectives might not work as well to describe a western gunslinger or comedic clown scene. Would they?Step 2. Choose Your WordsThere’s no wrong or right approach. If you want feel free to copy and paste vintage scene descriptions or sections of old movie reviews into your prompt. Yes, that can generate images, just be aware the copied text will need major adjustment.But, wait, you may be saying to yourself, aren’t prompts supposed to be well structured? Yes. But more important is consistency of directions. You can generate an image with:Cinematic, Hyper-realistic, dancing toads, chibi.Hyper-realistic, Nicholas Cage, superman punching Lex Luthor, Metropolis.Comic Book Art, Maisie Williams, Raven casting spells, Teen Titans.Technically those prompts have a subject and style/aesthetic description, which a good prompt needs to generate an image. Go ahead. Try them for yourself. That first prompt is simple. Your results shouldn’t vary too much. The second and third prompts will likely generate wildly different results. This is because what they lack is a coherent directive.Step 3. Write a Strong DirectiveWhat is a strong/coherent directive?Something like:A hyper-realistic cinematic action scene of Nicholas Cage as Superman punching the villain Lex Luthor into a building in the City of Metropolis.Go ahead. Try the prompt. You will get interesting images. However they may not necessarily be close to the described action.Why?When images are generated that do not precisely depict what was in the prompt it’s usually because of vague directions (meaning poorly written) or filtering. Yes, filtering. In comic books punches fly like raindrops in a hurricane. But certain AI generators may balk at depicting violence, unless you use a model specifically designed for comic book action scenes.Give the prompt another try rewriting it to depict whatever actor you’d like to see as (or with) your favorite superhero or superheroine, and no they don’t have to punch a villain. It can often be just as challenging to depict them rescuing a damsel/dude in distress or just licking an ice-cream cone. You just need a clear description and strong main subject.Step 4. Choose a Strong Main SubjectThis can seem highly subjective. If you are a fan of Game of Thrones, you will assume everyone knows who Maisie Williams character was. Likewise, to fans of comics, characters like Superman and Spiderman are considered well known (as is which comic imprint they belong to). It may have thus come as a surprise, if you count yourself amongst the ranks of the Fandoms mentioned, to see the results of the third prompt:Comic Book Art, Maisie Williams, Raven casting spells, Teen TitansBecause of her pop culture fame this will generate images of Ms. Williams. But will it definitely generate images of Ms. Williams as the Teen Titan Raven? If you tested the prompt you know the answer. You’re likely to get a better result with a simple declarative sentence like:Maisie Williams as the Teen Titan superheroine Raven.Another example. Consider the image this prompt produces:Cyberpunk, heroine, neon cityscape.Now compare with the image created with this prompt:A flamehaired Cyberpunk heroine eating noodles under neon signs against a futuristic cityscape.Once you have a strong main subject you can easily, and simply, refine your image with detailed aesthetic and/or style cues.Step 5. Consider Aesthetic and StyleAs a general rule the more detailed, and tightly written, a prompt the better the output. This means judicious yet creative use of descriptors paired with aesthetic and style directives.Aesthetic means anything that describes the desired visual style. A few examples: 3D, art-deco, artistic, bas-relief, cinematic, epic fantasy, fresco, game art, impressionism, oil painting, painting, photo, photorealistic, realistic, surrealism, whimsical, and etcetera.Style, while it can overlap with aesthetic, is really just how you stress what should have more weight in the image. IE: epic fantasy painting, photorealistic game art, sci-fi space-opera, Halloween horror, Christmas Fantasy, whimsical impressionism, and etcetera et al.Remember the cyberpunk heroine from our previous example? Think of ways to tweak the prompt to your liking by adding style and aesthetic descriptors and see what a difference those tweaks make. Don’t have time right now, no problem, try this:A flamehaired Cyberpunk heroine eating noodles under neon signs against a futuristic cityscape, cinematic, photorealistic, sci-fi, intricately detailed futuristic architecture, realism pushed to extreme.Wow, quite the difference, right?To get even more depth out of your generated images you can also expand the details. Right now that’s a static photo. But what else might be happening? Are there drones hovering above? Does she have a pet, if so what kind? What if this was a “bustling street scene” or she was “sitting under the shadows of flying cars”?You can create myriad creative flourishes in your art just by adding a few additional details. Try to avoid overwriting the prompt by stacking your descriptors. However, just as you want to avoid overwhelming the AI with too much detail so, too, will you need to be careful how you combine descriptors.Step 6. Temper Your DescriptionsThe two main difficulties, I have found, with attempting artistic precision is overwriting your descriptions and combining too many descriptors.How is that a problem? To keep a prompt below a set word threshold often means taking shortcuts like reducing a sentence to keywords : “night, cemetery, Halloween theme” or eliminating entire sentences by combining descriptors : “Happy Holidays, winter scene, day, golden hour, cinematic, cookies” in a prompt. It’s not necessarily bad methodology, but sometimes subtle contextual cues may be lost when a prompt gets simplified in this way.Did you notice anything different? Two additional variables are specified: night and day.When I chose the word “temper” for this section title I did so not just to mean “keep it simple” but to suggest you hone your prompts, if not to perfection, at least to include as much basic information as possible. You are not just any artist, you are a blacksmith hammering the imperfections out of metal to forge a strong sharp blade, your prompt. That means considering whether to include directions for lighting, background details, setting description, specifying an architectural style for buildings, amplifying style by including references to genre and artistic style (or specific artist's style, "in the artistic style of [insert artist name]") or any other details you think will help make your art look better.Just remember: A prompt doesn’t necessarily need to be overly bloated with directions for style, lighting, color, and everything else you might read about in guides. Just choose what seems right to you. You’ll quickly discover what works and what doesn’t, and that can be half the fun of creating AI art!Speaking of fun Here’s one last prompt to try. It’s a subtle difference from the images generated by the prompts above, but a good one. :A flamehaired Cyberpunk heroine eating noodles sits in a café on a busy street under a neon sign that reads: “Noodles”, a drone flies overhead, fog shrouded futuristic cityscape, cinematic, photorealistic, sci-fi, intricately detailed futuristic architecture, realism pushed to extreme.I hope the challenges posed in this article have been fun and helpful.

The season shall soon be upon us and, being an artist, you want to create something to say “Happy Holidays!” with your favorite AI generator. Perhaps you've thought about making your own Christmas cards, postcard, or just a fun season image. But how to make your image pop? The best answer I can give is to show you by presenting a prompt to play with. This is a favorite sample prompt style I’ve picked up: A redheaded woman wearing an Christmas sweater depicting Santa Claus sits reading a magical glowing book, the central focus, a flying reindeer leaping up from the glowing pages, shimmering Snowflakes forming the words "Christmas Magic" float in the air above the woman as Christmas plum fairies dance around the room, cinematic, hyperrealistic, volumetric lighting, incredibly detailed. That was used to generate the image attached to this article. Obviously this prompt needs a model that’s good with text. I’ve found Flux Schnell works decently for test images, but there are plenty of options for you to choose from. That said you probably don’t just want to copy and paste. So here’s where you get to show off your creativity. Ready? First, notice how the woman is described. You can change this. Perhaps your girlfriend is a blonde, or maybe you’d rather adjust the description to be male, or maybe you’d prefer a grandmother? No problem. Just change the description. Don’t like Santa Claus? No reason that sweater can’t depict: Rudolph the Rednosed Reindeer, Christmas presents, or a Christmas tree. This is just a sample descriptor. You can put in whatever you want. Likewise you can change the text from “Christmas Magic” to any greeting you want. The shorter the better. (Happy Holidays, Joyeux Noel, Seasons Greetings, and etcetera.) Go ahead and play around with that prompt to get a feel for it. It’s okay to rewrite it, I tried to keep it simple ans you should be able to do much more with it. In fact you can exoand it by describing the room. Do you want a cozy fireplace or Christmas trees? Then add them. Remember to write clear simple descriptions, at least to start with. Going Beyond the Theme I chose Christmas because, let’s be honest, that’s probably the easiest art for any AI model to produce. But you don’t need to create a Christmas image. Maybe you are a tabletop gamer looking to post a flyer looking for players. Consider this: A gamer girl wearing casual clothes sits reading a magical glowing book at a table, the central focus, a Amazon Warrior leaps off the glowing pages, shimmering smoke curls up forming the words "Gamers Wanted" that float in the air above the woman. Polyhedral dice, miniatures, and a Dr. Pepper soda are spread out on the table, cinematic, hyperrealistic, volumetric lighting, incredibly detailed. Remember there’s virtually no limit to what you can create. So why are you still reading? Wink. That’s it for now. I hope this was helpful.

It all begins with your prompt. You need a good solid prompt that clearly states what you want. The Prompt is how you direct the AI, so if your text isn't clear neither will be your output image.Getting StartedAnyone who’s attempted to generate concept or fan art of their favorite celebrities in scenes from popular series, or has attempted to generate crossover images, will have noticed certain AI models have these actors seemingly locked into a certain age and look. For instance prompting for actors of yesteryear like Ricardo Montalban or Lucille Ball tend to generate images of a distinguished gentleman and matronly redhead. (No need to specify hair color with Lucy.) While the opposite holds true for more recent popular actors like Jenna Ortega or Maisie Williams.If you’ve read my previous article discussing age prompts and attempted to apply that advice in reverse, sadly, it seldom works. And if it does the results may be even more inconsistent than attempting to write a prompt to generate a consistent age regression for an popular elder statesman actor. But it's not impossible, though you may need to have patience and burn through a few generations.Begin with a clear character description. What you’ll want, to begin, is to describe the target age with as few descriptors as possible. That seems to work best. Usually. Also, and this one is important, pay attention to your CFG setting.Some descriptors to try may include: older, old, grownup, aged, age [input your desired age], middle age, matronly, elderly, wizened, mature.Do they work?On occasion and depending on your chosen model.Remember: Write the prompt so it is telling the AI that your chosen actor or other personage is being depicted in a older role. For instance: “Jenna Ortega as the matronly Countess Bathory.” That might work. Results will vary depending on your chosen model. So experiment until you find the model that works for you.Sticking to a Favorite ModelWhat to do if you really have a great idea but can’t get the age quite right in the model you absolutely have to use?Option 1. Create the image you want without the actor’s name in the prompt. Then do a face swap/overlay.Don’t have access to that sort of tool?Option 2: Use complete sentences, no syntax shortcuts, with strong descriptors to spell out what you want the character in your image to look like. You can’t force a model to generate a style of image that doesn’t fit its aesthetic framework, but you can sometimes get it to come close.Examples:A) This seems to work 50/50: “Jenna Ortega aged 50 years as a matronly Countess Bathory.”B) This seemed to work better: “Jenna Ortega aged 50 years as a matronly Countess Bathory, wrinkly skin, old woman's face, haggard, tired face and eyes.”See the difference? Prompt A left quite a bit of room for interpretation whereas Prompt B narrowly defined the desired output. There are pros and cons for both prompts. For instance Prompt A, because it’s not as constricted, may generate a more authentic face whereas Prompt B may output a character barely recognizable to you.That’s it.While there are plenty of tools out there these are the basics, at least that I have observed to work within your prompt. No external image processing required.I hope this was helpful.Addendum: I very nearly forgot, and this is VERY important. Pay attention to your negative prompt, if you use one. The negative prompt also guides your image output. Check out my gallery. Look for the Countess Bathory images. The one with the younger looking Countess has my stock negative prompt. It's bloated and overwritten. A problem for another article. Edited for clarity.