Mudge

Mudge

Transforming ideas into art while learning how to write better prompts and create LORAs to share.
291
Followers
246
Following
2.8K
Runs
4
Downloads
9.2K
Likes
77
Stars

Articles

View All
So You Want to Make a LoRA (Final Part)

So You Want to Make a LoRA (Final Part)

This is Part 4, and yes the last part, of this introductory article guide to LORA creation. Here I will present links, many to LORAs and images I created while writing this, to provide a comparative sampling of what can be made without needing to know a lot of technical details. Seriously, I basically just uploaded the images and let the tensor.art training platform do its thing. So now you need to decide whether to...Step 3: Dive in head first or check out one of the tensor.art specific step-by-step guides for LORA creation.If you have a dataset ready and feel like you're good to go then get started, you can peruse this article at your leisure while waiting for your LORA to train. Or, if you're still uncertain, there are many great informational articles published here on Tensor.art. To begin I’d suggest skimming at least one of the step-by-step guides before diving in blindly. Here are links to a few:https://tensor.art/articles/875734357225025459https://tensor.art/articles/806929088523547379https://tensor.art/articles/849095063096129962https://tensor.art/articles/732090335657730218All steps in the process ultimately lead to...Choosing your LORABottom line the best LORAs cost the most to train. There are a few that you can bank credits for in a short period of time, depending on how many images you have in your dataset. The two best for this are probably the Lightning FLUX and SD 3.5L. But they are very different.How different?As a test I created a dataset comprised of 6 Dystopian, 5 Fantasy, and 9 Wasteland warrior AI generated images using the comedian Katherine Timpf as my character template. All that means is, instead of describing a character in detail, my prompt ask was “Katherine Timpf as a” or “depicting Katherine Timpf as” kind of syntax. To round the dataset out I included 6 images of a character holding a sign reading “Kat”, 4 ‘photoshop’ style AI retooled (background cutout/replaced, indrawn touch ups, etc) genre themes images, 2 upscaled headshots, and 10 random other images. That should make for a solid, if not better, dataset than using just 10-12 images, right?Let's find out. I have generated comparison samples for both versions of the WASTELAND WARRIOR KAT LoRAs: https://tensor.art/images/876085333362493423?post_id=876085333362493424&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/876061863513690934?post_id=876061863513690935&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/876062475546563295?post_id=876062475546563296&source_id=njeyo1nrnEW3oPYsaX309xkkThe first image sticks close to what the image set was intended for. The Witch art, which actually looks pretty amazing, was the best test I could think up that had completely no aesthetic similarities with the source images. I think they prove the Flux LORA is fairly versatile with prompt interpretation on its own whereas the SD 3.5L version seems less so. Flux costs more but the images should speak for themselves.For example this is what we get when combining WASTELAND WARRIOR KAT with other LORAs:Wasteland Warrior Kat FLUXhttps://tensor.art/images/876088023085772229?post_id=876088023085772230&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/876090879239001728?post_id=876090879239001729&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/876091719978895752?post_id=876091719978895753&source_id=njeyo1nrnEW3oPYsaX309xkkNot terrible. Now let’s try…Wasteland Warrior Kat 3.5Lhttps://tensor.art/images/877386430354090215?post_id=877386430354090217&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/877386722411870693?post_id=877386722411870694&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/877388513413183158?post_id=877388513413183159&source_id=njeyo1nrnEW3oPYsaX309xkkObviously the first couple with the polar bear were a quick test. Simple prompt. No reference to the character or character description. (She even disappeared entirely from a couple image generations, like the 3rd image above, for some odd reason.) Now here’s four with more or less the same prompt, but generating very different artistic styles:https://tensor.art/images/877534034421380333?post_id=877534034421380334&source_id=njeyo1nrnEW3oPYsaX309xkkWith SD 3.5L the prompt has to be worded very specifically whereas with FLUX you can write a few words and probably get a decent looking pic. Even the polar bear prompt generates a slightly different looking image without adding extra descriptors when using the FLUX version: https://tensor.art/images/877593127802635927?post_id=877593127802635928&source_id=njeyo1nrnEW3oPYsaX309xkkOf course you don’t have to use either. But, by now, you should have a dataset ready (if not already uploaded) and all that’s left to do is train your chosen LORA then…Step 4: Name and Publish your LORAI know what you’re thinking... What did Mudge do that necessitated spelling out the obvious final step as if it’s difficult?I chose a LORA name “Bare Ten” (because it only used 10 images), which sounded better than “Just Ten” in my head. Also I thought it fit well with my low-key “Barefoot” naming meme. The problem? I forgot “bare” is one of those words that is a red flag for auto-mod filters everywhere. It’s okay to laugh because that wouldn’t be a problem, except for the fact I often use my LORA names as trigger tags.You see where this is going. Too bad I didn’t. But I quickly discovered the problem as I had to log in to see images created using those tags. So now I feel kind of silly because it just never occurred to me. The fix was simple, rename the tags. Which I did. I even came up with a more descriptive name for the LORAs. The links to them (and a few more I created) are below.Ten Scenes Emilia: https://tensor.art/models/871749988005217621?source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/models/872118629343169865?source_id=njeyo1nrnEW3oPYsaX309xkkTen Scenes Pirate Girl:https://tensor.art/models/871704761999581375?source_id=njeyo1nrnEW3oPYsaX309xkkVintage Photo Nichelle Nichols:https://tensor.art/models/872788354331067482?source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/models/872497183465720805?source_id=njeyo1nrnEW3oPYsaX309xkkWhat the above all have in common is they’re either trained on 12 images: 10 main scenes and 2 poster art mockups with title text or fewer than 20. I don’t know if it helps to train a LORA including images with text or not but I figure it can’t hurt. Besides I am testing my work prompt anyway to be sure it creates a decent looking title so might as well use the sample images, right?Well, that’s it. Thanks for reading. I hope this helped. All that’s left is a refresher on the…Simple Annoying Stuff:IMAGES: Whether curated from an public domain image archive or sourced from free range pictures you corral and lasso in an image search, there’s always two things of primary importance. First, clarity. Second, quality. The better your source image the better your training will be, which means a better model result.UPSCALING: Not necessary for images of decent quality. However, for the best results, use a tool that outputs images of high-quality but not necessarily large file sizes.IMAGE OPTIMIZATION: This is sort of related to the above. If you have a tool that outputs too large of a file size this may become necessary. However, and here’s a trick I discovered by accident. Some tools will only ever produce images in the 1+ MB size range. Problem is optimization often loses some of the quality. What to do? Find a tool that outputs smaller already optimized files. Often you can upscale images through another tool and not only get an optimized file but a fairly decent image with more pixel resolution. Doesn’t always work but when it does, golden.RETRAIN: Before your LORA expires you can RETRAIN it, meaning use all your already uploaded pics and generated tags, to create a NEW LORA. And, no, it doesn’t have to be the same model you already trained on.Now Let's Go Make a LORA!Tap the menu tab at upper right of screen. On the drop down menu you should see "Training" (just above "Creator Dashboard"). Click on "Training". This will take you into the first of the LORA training pages. From here you begin the process of uploading your images, or a prepared dataset in a ZIP archive. For noobs like us we will be batch uploading images and let Tensor auto create tags. Now you can add specialized tags and prune the auto-generated tags, but that’s a whole different article. Once the images are uploaded and the tags generated pick a LORA. Do you have the credits? If so, great! If not you have a couple choices: 1) Bank more credits. 2) Pick another LORA. 3) Use fewer EPOCHs. Once your settings have been adjusted to your liking and you've filled in all necessary information begin a training session. If it fails don't panic. Try again in a few hours when there's less traffic on the site.Congratulations! You've made a LORA!
So you want to make a LORA? (Part 3)

So you want to make a LORA? (Part 3)

Okay you’ve read this far (thanks for sticking with me) and have decided that you’re going to give this LORA thing serious consideration. Great! But what now? Well it's time to…Step 2. Curate quality source images for model training.Once you have a solid idea, be it a character or style, you need a good reference dataset. That means images. To make a LORA you need thematically relevant reference images. These images are used to train the LORA.The standard that seems to work best is to collect or create between 10 to 80 high quality images that fit with the theme of the LORA you want to create.What? 80 fracking images…to create from scratch!?That may sound like a lot, and it is, but the good news is you can source your sample images from anywhere. You don’t actually have to generate your own training images, its just often quicker to get the specific type of artworks to fit a theme this way. Per chance, if you have an account on another platform, there’s no reason you couldn’t generate images and use them. In fact it might be better to curate images from multiple sources as a quality control. Your trained LORA will not suffer if the reference source images aren’t all generated on the same platform, or even using the same base LORAs. What’s important is resolution quality, not quantity, and consistency.Where to start?The highest bestest most awesome source images won’t be worth a can of refried beans if you choose the wrong type of Base LORA. So far I have only tried Lightning FLUX and SD 3.5L, not because of cost but because those seem to be good with most Character LORA styles. AND those were the Base LORAs I’d used to make art with when I started. There are many other style options, like for Anime, but I picked a familiar LORA that generated a style of AI art similar to what I wanted to create.Honestly I'd just stick with FLUX to start with. It seems decent, even when only using 10-12 images. Best of all the learning curve wasn’t that steep. However to generate a consistent look, style, or character pose you do need some repetition.How much repetition?I’ve found 2-4 similar images seem to work okay. You can do 30. But that’s just silly overkill. No, seriously. I had no clue and used 30 similar images of Bacchae dancing at a Dionysian revel or Mountain glade initiation. The result, even at a LORA weight of 1, is bleed through, mostly of grapes. Lots of grapes, even when not prompted for. No need to shame the LORA, not her fault. But, because of that mild snafu, I’d suggest repetition of images in larger LORAs should probably be kept to 10 or fewer similar images and then only for a full range of front (2), back (2), and side views (2 left, 2 right) of the subject and, for Character LORAs, at least 1 to 4 good quality head or head and shoulder shots.To recap, whether generating AI images or searching for art/pictures consider the character poses/subject positioning. Of course how many images you decide to use will depend upon what tier you are at and what you want to create. Free tier community members can make LORAs, and relatively decent ones, even if we are limited to 100 images. So far I’ve not required that many for a dataset. So don’t worry about it. Start simple with a test LORA of 10-20 reference images. See how that goes.Remember that what type of LORA you can create will depend on how many credits you have banked since the more source images you employ the higher the cost to train will be. An important consideration to keep in mind. The good news is, once in the online training menu, you can toggle through the various options. After all your images have uploaded and the tags have been applied you will be able to see how much each particular LORA would cost to create. So, whether free tier or Pro, it doesn’t hurt to toggle through each option you are considering and compare the cost.For the best result your images should be good quality with decent resolution. If you have the image editing tools clean up the image if necessary. That means remove extraneous logos, screenbugs, and other unwanted text or image elements. Remember these are TRAINING images. That means if you use screencaps with a station logo or image with a screen bug (like a URL) that will become part of the training model.In Practical Terms: The more images the more time it will take to train. AND the more it will cost. Cleaning up images with logos or other visible watermarks is a must. If you can upscale do so for lower quality images but if the result after upscaling isn’t crisp and clear trash it. (Pay close attention to the eyes when working with character images. Not all upscale tools work the same.) Use only clean, in focus, high-quality images when possible; unless you are doing a Style LORA that requires film grain or blurriness.Thanks for reading this far. If my terse writing style hasn’t turned you off to creating a LORA then you are ready for…Step 3: Dive in head first or check out one of the tensor.art specific step-by-step guides for LORA creation.(PART 4: https://tensor.art/articles/877929254090760909)
So you want to make a LORA? (Part 2)

So you want to make a LORA? (Part 2)

So you want to make a LORA but aren’t sure where to start? Well let’s begin simply from…Step 1. Decide what type of LORA you want to create, and what you want it to do for you.If you feel confident you’ve got this and are ready to create skip this section and move on to Step 2. This section is mostly for those still not sure about LORAs, or who are just curious and looking for ideas. If that sounds like you read on.Whether you are thinking about creating your first or hundredth LORA it all begins with a Theme. The Themed LORA aka a Character or Style LORA is probably the most basic, and easiest, LORA to curate images for since you’re starting with an idea in mind. Our goal is to manifest that awesome idea as a visual representation, an AI generated image. Take a look at my 1) STARGATE-SX and 2) BAREFOOT BACCHAE LORAs as prime examples. Both were created around solid central themes: 1) a retro-futuristic Sci-fi series with a Stargate vibe. 2) the historical Bacchae female character of Ancient Greece.I curated the source images by creating original images. Mostly. (I threw in a couple of screen caps for the Stargate LORA.) Yes, it took days. Probably weeks, subjectively, to create and source them. Why so long? Because we want the best images possible. Not every image you create will be usable. Of course you will have to establish your own standards. Personally I try to use only images with the correct number of hands and toes that require as little in-painting as possible. Clear character facial features, especially the eyes, are also good, but I can’t stress the importance of realistic looking images, or the correct number of fingers and toes.Yes, toes. There’s a reason, beyond the happy accident of naming my first LORA Barefoot Comix Anime Girl, that I call some of by LORAs “Barefoot”. The reason is simple, they often contain source images where characters are barefoot or in so-called ‘foot centric’ poses. Same with hands. Hands aren’t usually a problem, but feet seem to come out looking wrong in too many images. So I try to find or create images with solid good looking feet. This is probably easier for Character LORAs as you can just search for “[Actress Name] Feet”. Just be sure Safe Search is turned on. Trust me, your eyes and brain will thank you.That’s actually how my first LORA came about. An effort to provide a useful corrective style LORA. I figured, by compiling barefoot anime style images and illustrations, and making a LORA that might be a useful corrective style LORA. Did it work?Check out the gallery of images for any of the BAREFOOT COMIX ANIME GIRL LORAs. You decide.To really get an idea of what is possible I humbly suggest checking out the LORAs created by the following Tensorians:@Calinepadraigin https://tensor.art/u/774825513653961520@TT210 https://tensor.art/u/766259832742236088@Realistic AI Portraits https://tensor.art/u/797858349520640926@Bloody669 https://tensor.art/u/614212488610944584@Marlok https://tensor.art/u/632364738390630312I have quite a few of the above Tensorians fine LORAs in the “My Starred” tab. Some I have used more than others. All are excellent examples of the diverse styles and types of LORA you can create. Hopefully, as you peruse the galleries and look at LORAs, something will inspire you. Once that spark lights the Muse’s fire you’ll be ready for…Step 2. Curate quality source images for model training.(PART 3 link here: https://tensor.art/articles/877381456781910512)
So you want to make a LORA? (Part 1)

So you want to make a LORA? (Part 1)

So you want to make a LORA, but aren't sure where to start? Hopefully, after reading these articles, you'll decide this is something you'd like to try. I've tried to include examples and helpful resource links.If you’re like me you have probably found yourself sitting there after your image generated, staring at the screen, thinking: ‘I don't like how this looks.’ Wishing you had a better LORA to use for your artwork. Or maybe you were muttering something with more colorful metaphors because, well, things and stuff happens.Well, curse at your screens no longer! Making a LORA, at least here on Tensor.art, is surprisingly simple.No. Really. If I can do it so can you.There are many how to guides for LORA creation that will take you step-by-step through the process. This article isn’t one of those. This offers some practical advice and, hopefully, useful information based on my own observations (good, bad, and d’oh!) from creating a couple of passable LORAs.To begin have a basic idea of the what and why of your goal for creating a LORA. Even if it’s just to see how it’s done, you need a good basic thematic end result in mind. Meaning what type of character or art style you'd like to create with your LORA. Anything is possible from Dark Jedi, Barbarian Warrior, Frank Thorne art style, Pies, race cars, Whimsical Kittens, Post-apocalyptic Landscape, and etcetera et al.Main question: What kind of art are we wanting to create?Not sure. Then ask yourself: What character or style do I need (or want to create) that there isn’t already a LORA for. Or that no LORA exists for your preferred generative Model. Or that you just would like a better version of. (Not all LORAs are created equal. You can try three similar character LORAs and often get very different results.)For example there are many Character LORAs for actress Kaley Cuoco. But there were none of her as a fantasy warrior. Of course with the right LORA combos you can create awesome Kaley Cuoco Barbarian Warrior artwork. But what about a blood-splattered Warrior? Sure, we can create that, but using how many LORAs to get the image just right?I took this idea and created BARBARIAN WARRIOR KALEY using 25 images in the training dataset. The images I curated include 7 head and shoulder shots, 3 mid close-up body shots (head to knees), 10 full body shots in dynamic poses, 1 artistic image, and 4 sample images using a test prompt similar to the one used to generate the LORA sample images generated during training then in-painting to touch up the face and eyes.Here’s the published LORA link: https://tensor.art/models/876777897912706295?source_id=njeyo1nrnEW3oPYsaX309xkk so you can view the gallery of generated images. This LORA appears to do dungeon backgrounds and blood-splatter very well. In fact it may seem too bloody, depending on your prompt, and not enough like Kaley even at the default weight of 1. Lowering the weight to .8 lessens the persistence of blood-splatter, but this may affect the likeness since the source images were AI generated facsimiles. But it's good enough we can use it with a Character LORA, if we want a more realistic likeness.Now, having seen some of what is possible, all you need is to…Step 1. Decide what type of LORA you want to create, and what you want it to do for you.(PART 2 HERE: https://tensor.art/articles/876855087064988656)
Creating Magazine Covers

Creating Magazine Covers

So you want to make a magazine cover?Warning: Some of the linked to images may have been tagged as NSFW by the automod. And even if they haven’t the thematic is a sword-and-sorcery Sorceress, meaning scantily-clad. So if you do not have NSFW toggled on you may not see all the test samples.That said the basic formula used in nearly all the prompts linked to created specifically for this article begin with: “Cover of pulp cinema magazine " [YOUR TITLE HERE] ", cover title: "[YOUR TITLE HERE]", sub title: "[your info here]", depicting [insert your prompt info here]”That said I just have one question...Have you ever wanted to make your own cover of a comic or magazine but worried you lacked the skills to do your idea justice?Well, friend, fret no more because with AI you can do a lot more than even photoshop can achieve! Why. Yes-sir-ee, this here AI can make your wildest fanzine fantasies all but come to life!How?It’s actually easy, once you get the hang if it, the gist, the general idea, the… Well, a good base prompt to work with. You don’t have to use the ine in this article, though it’s a good starting point. Myself, I began with remixing prompts here on Tensor. You can learn a lot by reading and editing (whether you hit the remix button or copy and paste) prompts. As with most AI art you want to start with at least the outline of an idea.What do YOU want to create?Maybe you've always wanted to see an issue of Savage Sword of Conan where Conan wrestled in mud with Red Sonja, a comic cover of The X-Men where Harley Quinn teamed up with Wolverine, or maybe you want your own magazine... A fun faux fanzine (or mock-up for a digital fanzine) something like one of these:[Warning: The theme for many of these was “Exploitation Cinema”, thus many will probably be tagged NSFW.]https://tensor.art/images/842285048855026533?post_id=842285048850832231&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/842779283626799485?post_id=842779283622605183&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843415668931080877?post_id=843415668926886575&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843556165901327491?post_id=843556165897133188&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843778396099111037?post_id=843778396094916735&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843477336071517678?post_id=843477336067323375&source_id=njeyo1nrnEW3oPYsaX309xkhttps://tensor.art/images/843409458408235776?post_id=843409458404041473&source_id=njeyo1nrnEW3oPYsaX309xkk[More in my gallery. Remix and twerk, er, tweak away!]While those may be great examples what you really want to know is where to begin. For me, I have split my prompts into two parts. First, the description of what type of magazine I want to create. Second, the type of illustration I want on the cover. With a good solid first part you can actually generate decent concept cover art. And a good second part will generate a solid image as is. As I will now demonstrate.Prompt 1: Cover of pulp cinema magazine " SAVAGE LENS ", cover title: "SAVAGE LENS", sub title: "Exploitation Cinema", depicting Hyper-realistic, cinematic film still of a 1980s Barbarian fantasy movie, epic fantasy action scene in vivid Technicolor, well-defined hands, beautiful face and eyes, realism pushed to extreme, whimsical gothic fantasy Eroticism, perfect body, beautiful, realistic, masterpiece, dynamic movement, volumetric lighting, realism pushed to extreme, vintage cinema magazine cover.https://tensor.art/images/843882055134686903?post_id=843882055130492600&source_id=njeyo1nrnEW3oPYsaX309xkkPrompt 2a : The image shows an beautiful young provocatively posed 21-year-old Arabian girl as a sensual insufficiently attired sexy barefoot Sorceress, skyclad with a sheer see-through, off-the-shoulder sheer sky blue chiton cape draped over her nude body, athletic young body shown in intimate anatomically correct detail, mystical runes painted upon her bare skin, long lustrous windswept hair, toned body, intricately detailed nubile young athletic figure, legs spread in dramatic stance as she leans back in a forest pool, wet, posed in a tantalizing tableau that accentuates the sensual intensity and elegance of a young Arabian girl's feminine presence and mysterious mystical power. A flimsy transluscent emerald cloak billows around her, rippling like shadows in the oppressive gloom of a grimdark forest, where the columns of ancient Greek ruins rise up like skeletal fingers. With her right hand, she holds a stick, poking into a vine covered altar where a pulsating otherworldly light shines from a small statue. With an intense expression, her piercing eyes spark with power as she conjures swirling orbs of vibrant magic above the open palm of her legt hand, casting ethereal wisps of defensive energy into the blackened air. The forest is alive with a sense of foreboding, gnarled roots, detritus, and a thick fog clinging ominously to the ruins. This Lovecraftian nightmare setting is a tableau of dark danger and adventurous allure designed to captivate the viewer with sensual intensity and a gratuitously insufficiently attired beautiful barefoot young Sorceress, well proportioned limbs, Perfect hands, museum-quality nude, intricately detailed background, uncensored creative flourishes reminiscent of classic Greco-Roman nudes, Occidental Eroticism, Arabian Fantasy, beautiful bald pussy, perky nipples, ultra-realistic labia, well proportioned limbs, well-defined features, beautiful barefeet, beautiful pussy, ultra-realistic, 4k, 8k, 16k, UHD, realism pushed to extreme, 5 fingers, trending on Artstation, DeviantArt, Rule34https://tensor.art/images/843883571258176309?post_id=843883571253982007&source_id=njeyo1nrnEW3oPYsaX309xkkWowzers! What a lot to read, right?That prompt can be edited down quite a bit. I put in extra description specifically for you to play with. (Actually I based a lot of it on the extraneous descriptors in prompts read here then copy-pasted into the prompt. Not complaining. Just saying.) In fact, if you read carefully, there are utterly pointless descriptors included. Some that will no doubt leave you scratching your head. Trust me, there’s a lot to work with. To begin you can take the above and trim it like this:Prompt 2b: The image shows an beautiful young provocatively posed 21-year-old Arabian girl as a sensual insufficiently attired barefoot Sorceress in a sheer, off-the-shoulder, sky blue chiton cape draped over her athletic young body, mystical runes painted upon her bare skin, long lustrous windswept hair, legs spread in dramatic stance as she leans back in a forest pool, posed in a tantalizing tableau that accentuates the intensity and elegance of her mysterious mystical power. A flimsy transluscent emerald aura billows around her, rippling like shadows in the oppressive gloom of a grimdark forest, where the columns of ancient Greek ruins rise up like skeletal fingers. With her right hand, she holds a stick, poking into a vine covered altar where a pulsating otherworldly light shines from a small statue. With an intense expression, her piercing eyes spark with power as she conjures swirling orbs of vibrant magic above the open palm of her legt hand, casting ethereal wisps of defensive energy into the blackened air. The forest is alive with a sense of foreboding, gnarled roots, detritus, and a thick fog clinging ominously to the ruins.https://tensor.art/images/843886629274967383?post_id=843886629270773080&source_id=njeyo1nrnEW3oPYsaX309xkkNot bad. So, there you have it, two separate prompts. Now let’s combine prompts. I, of course, chose Prompt 1 and 2b and here is the result:https://tensor.art/images/843891156170366668?post_id=843891156166172365&source_id=njeyo1nrnEW3oPYsaX309xkkGranted that took four tries. The first three:https://tensor.art/images/843892869862360374?post_id=843892869858166072&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843893423913154106?post_id=843893423908959804&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/843896271476536731?post_id=843896271472342428&source_id=njeyo1nrnEW3oPYsaX309xkkSo, what happened?As you can see, no text. Oh no! 😉Do Not Panic.At the same time I generated three images offsite. Each generated, in that Flux model version, near perfect title text.The point?Sometimes you may need to make tweaks so a prompt will work, or at least output an image you want. In such cases it’s always a good idea, if you can, to test your prompt on multiple platforms. (Or at least a separate platform.) Even when technically using the same model you may discover very different results. In this case it only required minor prompt tweaking and a few additional descriptors added to the end of the prompt. And, just to be sure it really works, one last image:https://tensor.art/images/843898195621927383?post_id=843898195617733080&source_id=njeyo1nrnEW3oPYsaX309xkkWhile it is customary to point out how your mileage may vary, instead I would like to point out that, by using various LORAs, you can generate some truly amazing custom results.In conclusion I would like to thank @Snowflake (amazing work with Weird Tales cover art), @juiwaters, @NickEden (great Sorceresses), @Jozz, @PEPA_AI (inspired my Weird Tales covers) and all those other posters of fantasy art and magazine cover mock-ups whose art inspired my recent foray into creating magazine cover art. Than you for your wonderful art and…Thanks for reading.I hope this has been helpful.

Text to Video: Is it worth the credits? (Part 1)

Text to Video: The Tensor BasicsDisclaimer: This article links to images and videos, some of which the auto-mod may have tagged as “NSFW”. The thematic genre of the prompt used is “1980s sword-and-sorcery” in the artistic style of Frank Frazetta, Boris Vallejo, and Julie Bell… Which does tend toward a certain insufficiently attired aesthetic. (Think chainmail bikini-clad warrior Red Sonja and scantily-clad Sorceresses.) So you may want to keep that in mind. If you don’t have “Mature Content” toggled to on any links to images tagged as “NSFW” may not work. Sorry about that. I did put “safe for work” in the prompt after the first few but… better safe than sorry.That said this article is about using text to video, specifically comparing outputs. The best way to do that is testing one simple prompt in multiple models. I figured the best way to test the various models available here was asking them to generate a person walking toward the camera. Too simple, you say? I agree. That’s why I asked for a sorceress. No point using credits if you’re not testing the model’s limits, right?Of course, by now, most reading this probably think they have pretty much “mastered” the basics of text to image prompt crafting and figure text to video is just as simple. Is that you? I know it was me. And boy-howdy was I wrong!If you want to try creating video from a prompt, or have already tried, maybe by copying and pasting an existing prompt, like I started out doing, you will quickly discover that those prompts don’t quite work. Or the result didn’t turn out as you expected, despite generating a half dozen test images. I thought that was good enough. It wasn’t. Happens to us all. Maybe it’s happened to you?Problem is video generators are costly to use. Typically they require way more credits than generating an image. Even at the “free” level most other platforms only allow for 2-3 generations per day. And, too often, that’s just not enough to learn much of anything by trial and error.So, what to do?Not give up. That’s where this article begins. With the basics. Rule #1: text to image prompts WILL NOT ALWAYS WORK for text to video generation. (More rules to follow in other articles, if there’s a need.) Practically speaking this rule means, if you have a prompt that you’d like to use, a prompt that works really well, you will need to tweak that prompt for use by txt2vid generators. It’s a pain, but not really that hard to do. In fact once you learn the basics of what does and does not work it gets easier. But, even after reading this article, it will take some trial and error. So don’t give up.Let’s get started looking as some basic test images using the same (or only slightly tweaked) prompt:https://tensor.art/images/829469892941049736?post_id=829469892936855433&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/829468638810575778?post_id=829468638806381475&source_id=njeyo1nrnEW3oPYsaX309xkkhttps://tensor.art/images/829387914900387766?post_id=829387914896193464&source_id=njeyo1nrnEW3oPYsaX309xkkThe images in the above links use a prompt similar to, but not identical with, the sample prompt we’ll be playing with later in this article. Also, they had multiple LORAs applied to create a specific artistic aesthetic. LORAs won’t be available for most txt2vid models here. Something to keep in mind when crafting a prompt. Go ahead. Take a second re-reading the prompts if you want. Okay. Great. Notice anything about them? You’re right. They’re relatively simple, if verbose, lacking the usual string of descriptors. And that’s a good thing.Why?If you read my previous articles on creating images I noted how it is possible to generate an image with simple prompts like: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.As it happens the first two prompts might actually work, as they contain directions that are also actions, but that last one probably won’t work very well. A good text to video prompt should be like a mini script, providing camera directions and specifying action and/or movements like:1) Camera pans on a cinematic action scene of dancing toads depicted in the chibi style.2) Technicolor film scene, light grain, a dramatic cinematic scene of Nicholas Cage as superman punching Idris Elba as Lex Luthor on a Metropolis skyscraper rooftop.3) Comic Book action scene of Maisie Williams floating in the sky as Teen Titan Raven casting spells at a horde of charging DC super villains turned zombies.Those should work. But will they? Without hot linking offsite (and the magic of reading an article long after it’s been written and edited multiple times) I can positively say…1) Yes, I got dancing frogs. Needs more of a description as it was very basic.2) Sort of. I did get Nicholas Cage, actually two of him. Fighting himself. He knocked himself off the rooftop into the horizon. (Kind of a cheat. I used director mode and inserted camera direction prompts.) So a technical fail. But hilarious.If you try this prompt maybe using a different actor will generate better results? You may also try describing Lex Luthor’s appearance to better distinguish him from Superman or just choose a different villain.3) Not at all. It did look like a comic book panel, sort of, if traced by a 5 year old. Hardly any actual animation. Very badly drawn. Horrible looking, actually. Don’t waste your time or credits trying it. Use this prompt instead:Dynamic cinematic action scene of Maisie Williams as the Teen Titan Raven. Raven is floating above a hoard of zombies, clawed hands reaching up toward her. As Raven hovers above the milling zombies, who resemble characters from the DC Comics universe, tendrils of black mystical energy leap from her fingertips dramatically destroying the zombies that her dark magic touches.That is the type of generic prompt that works best. By which I mean it provides a solid foundation to build on. You can insert camera directions, easily expand upon it, and it actually works as written without additional descriptors. At least my one test of it did.But what about those prompts from the beginning of the article?Good question. Thanks for remembering.Check out the prompt of this (typos and all): https://tensor.art/images/829469892941049736?post_id=829469892936855433&source_id=njeyo1nrnEW3oPYsaX309xkkBelow is a simplified version of the prompt used to generate the image linked to above. The below prompt will work, in both txt2img and txt2vid platforms, with varying degrees of success depending upon the chosen model. Since most of what was pruned was descriptive fluff, in other words description bloat, this also serves as a quick lesson in prompt craft. Remember try to keep your prompt concise and simple. Unless you’re on a platform giving you more than a 5 second video output, then have at it.Here's the shortened prompt:Hyper-realistic, creative, Frank Frazetta and Boris Vallejo inspired cinematic action scene of the beautiful Milla Jovovich as a insufficiently attired sorceress stalking through a torch lit dungeon catacomb toward the camera. Her radiant statuesque form moving with elegant precision, right hand holding a gleaming wizard's staff capped with a silver skull. As Milla walks she looks around, waving her staff around defensively, as if expecting a lurking monster to leap out of the shadows. From her wary expression Milla is ready to cast a deadly spell at any attacker. Her smile is pure malice, her face exquisitely detailed with symmetrical, well-defined features—high cheekbones, full lips, and piercing, otherworldly eyes with golden iridescent flecks. A shimmering halo of magical energy surrounds her as a a magic shield. Her long, lustrous windswept hair whips around her, each strand meticulously rendered, subtly shifting as if a writhing serpent.Okay. Here we are. We have a prompt to play with. Now what?(Continues in Part 2)Part 2: https://tensor.art/articles/829676356309759027Continues in Part 3 (Hunyuan vs SkyReels)https://tensor.art/articles/837497543295351531
18
2
[Image to Text] A useful tool?

[Image to Text] A useful tool?

Many may have noticed there's an image to text feature in many AI generators. If you're like me you've probably just shrugged it off, after all why waste credits on that?Well, while searching for something else, I stumbled on a free img2txt tool. Probably not as good as the one here but, intrigued, I uploaded a movie still. What I got was not that spectacular a description, yet useful. The kind of basic description that's easy to work with.Here's the prompt I created from one of the outputs. Text in green is the AI generated text. Text in yellow was my edit. Text in blue were my additions to the prompt.In a dimly lit, mysterious temple chamber, three women stand in a circle, with one in a striking red robe dramatically raising her arms as if invoking a powerful spell. The second woman exudes an air of apprehension, while the third observes with intrigue. In the center, a figure lies on a table, draped in white. Explore themes of mysticism, women's empowerment, and the tension between fear and curiosity. Hyper-realistic, cinematic, Technicolor, creative, extremely intricate detail, majestic, mythical, museum-quality, anatomically correct, realistic, realism, lifelike textures, Occult Symbolism, chiaroscuro, volumetric lighting, hyperdetailed, art trending on Artstation, DeviantArt, classic insufficiently attired occult art in style of Frank Cho, Stephen Youll, Don Maitz, Frank Frazetta, Luis Royo, Julie Bell, Frank Kelly, Ninjartist.Not a terrible prompt. I'd probably change a lot more, especially that last sentence (in the original green text prompt), to give it a more sinister horror movie vibe. However it works okay as is. Granted the images created with basic models sometimes don't look that great. Save, of course, for Flux, which was used to generate the cover image. What's interesting is how simple the descriptions created were.If you just need help describing a scene I'd say give the text to image tool a try. I certainly will in future. Especially for movie stills.Have fun.
1
Crafting Fun Christmas Greetings

Crafting Fun Christmas Greetings

No need to have read my article on last minute greeting cards, though the idea here is very similar. The difference? This article is about crafting a greeting card with a personal touch, assuming you have one important factor: Time.The good news, with most AI image generators you can craft some amazing seasonal greeting cards, and it's very simple.Step 1. Choose your AI model. My preference is Flux Schnell. For a traditional greeting card look my aspect ratio preferences are 2:3 or 9:16. Feel free to use what works best for you.Step 2. Write your prompt.Here's the one used to create the digital seasonal greeting card image attached to this article:In a cozy house warmed by a log fueled fireplace, a young woman wearing a Christmas sweater depicting a snowman sits reading a glowing magic book, the central focus, from which a winter wonderland scene pops up. Framed behind the young woman are windows through which can be seen an idyllic snow-covered winter landscape. Top centered curling holiday text reads: Merry Christmas.Step 3. Save to local device/HD. Print or Attach to message. Send to friends and/or relatives.That's it.Remember: You can get as detailed as you want with your prompt. No need to rush. Take your time and consider the image you want to create. Describe it. I kept my example simple. But consider these prompts:In a cozy house warmed by a logs burning in a stone fireplace an young woman wearing a Christmas sweater depicting a Christmas Tree sits reading a glowing magical book, the central focus, from which Santa Claus in his Sleigh pulled by magicalflying Reindeer leaps forth. Behind the young woman are windows through which can be seen an idyllic snow-covered winter landscape. Top centered curling holiday text reads: Seasons GreetingsTraditional Christmas Art of a young woman wearing a Christmas sweater sitting reading a glowing magic book, the central focus, from which a sparkling Christmas scene pops up.I created images for each. You can find them in my gallery. Notice the differences, and that's without adding a lot of descriptors. But that's just to start with. Be as inventive as you want to be!Don’t worry if you don’t get text, or the text you get doesn’t look how you want. You can always create more images. You have plenty of time to tweak your prompt. If, however, you don’t ever get text you will either need to pick a different model, like Flux Schnell, that works well producing text or use image editing software.Actually that’s what most of us usually do, apply text and stickers and all manner of third party art to our source images. But, with the right model, and a well worded prompt, you should be able to generate very nice holiday card AI art without needing to do all that.Oh, one last thing, check your negative prompt if you use one. If you have “text” in there that could pose a problem, as might certain other terms.Note: You may need to generate more than one image to avoid unusual results, but that can be half the fun.For more prompt ideas check out my article: https://tensor.art/articles/795640016094197726Happy Holidays!
Quick & Easy Greeting Cards

Quick & Easy Greeting Cards

Need a last minute greeting card with a personal touch?Good news, your AI image generator can do that. And it's very simple.Step 1. Choose your AI model. My preference is Flux Schnell.Step 2. Write your prompt.Here's the one used to create the digital greeting card image attached to this article:Thanksgiving card Art, idyllic first Thanksgiving scene, artistic, creative, 75mm, top holiday text reads: Happy Thanksgiving!Step 3. Save to local device/HD. Attach to message. Send.That's it.Addendum: You can get as detailed as you want with your prompt. I kept it simple. But consider these prompts:Thanksgiving card Art, idyllic first Thanksgiving scene with pilgrims and Indians, artistic, creative, 75mm, top holiday text reads: Happy Thanksgiving!Thanksgiving card Art, idyllic family Thanksgiving scene of multi-generational women and children in kitchen preparing Thanksgiving feast, artistic, creative, 75mm, top holiday text reads: Happy Thanksgiving!I created images for each. You can find them in my gallery. Notice the differences, and that's without adding any additional descriptors for style. Be as inventive as you want to be!Note: You may need to generate more than one image to avoid unusual results, like heads in cooking pots, but that's half the fun. Happy Thanksgiving!
Making Christmas Magic (Part 2)

Making Christmas Magic (Part 2)

This is just an Addendum to my introductory article on making Christmas Magic. Creating a fun seasonal postcard type image is fairly simple. If you like whimsical art then your descriptions should reflect this. Simple descriptions work best. Remember the more detailed and focused your prompt the closer to what you imagined that picture may be the AI output will get.Good descriptors are key to creating seasonal themed art. In fact, in many instances, you can just add a few keywords to a Favorite prompt to tweak it's aesthetic.Keywords and descriptive ideas you may want to use in your prompt: Christmas, Yule, Yuletide, seasonal, holidays, mistletoe, Christmas Fantasy, Christmas Magic, Christmas decor, holiday decorations, Yulelog burning in fireplace, with a mistletoe border, with a Christmas tree in background, Christmas Elves...You get the idea. 😉Here's a fun prompt to play with:(Christmas Fantasy:1.1), elfin Elves, Christmas Magic, triadic colors, windswept hair, extremely high-resolution details, photographic, realism pushed to extreme, fine texture, incredibly lifelike, dynamic lighting, upon a smokey tavern stage in the City of Christmas three beautiful barefoot Christmas Elves wearing Santa hats and red and green Christmas Elf costumes battle each other with candy cane wands filling the air with the colorful sparkling word "Noel" during a Yuletide magic festival, above them a festive Christmas banner reads "Yuletide Magic", epic fantastical Christmas art, epic fantasy, vintage Christmas postcard art, Hyper-realistic, windswept hair, intricate detail, majestic, high-quality resolution, UHD, highly detailed face,distinct facial features, photorealistic,75mm, 20 million pixels,4k,8k,16k,UHD,realism,realistic,vivid,key visual, film still, cinematic color grading, depth of field, sharp focus, professional photography, masterpiece, ultra detailed photorealistic, raw, anatomically correct, Hyperrealistic, splash art, concept art, mid shot, intricately detailed, color depth, dramatic, 2/3 face angle, long shot, side light, colorful background, whimsical.Addendum: A quick explanation. Everything after "hyper-realistic" are descriptors trying to do one thing, get a higher quality better clarity more realistic image. Is it all necessary? Probably not. You can delete it entirely and replace it with something like... "artistic, creative, extremely intricate detail, Christmas art, vintage holiday postcard art, art in style of Stephen Youll, Don Maitz, Howard David, Julie Bell, Frank Frazetta, Luis Royo,, trending on Artstation, DeviantArt, classic Christmas scene." And still get a decent, if very different looking, image. Or not replace it at all. Go ahead, give it a try.(When done here check out my articles on crafting holiday cards. What you learned here should prove useful.)Remember the image attached as a cover for this article used the above prompt with Lora's to tweak the result, but you can use whatever model you want. That image and more can be found in my gallery. Plenty of prompt ideas for you to remix or copy-and-paste.Here's that same prompt without Lora add-ons:https://tensor.art/images/799639532594004905?post_id=799639532589810603https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=1024,f=jpeg,q=85/posts/images/794519944456031492/200f186e-c522-4cf8-8b4d-6c31cfccc832.png[Is there a way to post images inside articles?]I hope this has been useful.
Crafting A Better Prompt

Crafting A Better Prompt

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.
14
Making Christmas Magic

Making Christmas Magic

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.
2
Generating Age Appropriate Characters

Generating Age Appropriate Characters

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.

Posts