Luis M Ruiz

Text Only Prompt: A cyberpunk cityscape with metallic structures, blending the styles of H. R Giger's biomechanical artistry and Jean Giraud’s space opera illustrations, all captured in the cinematic, high-contrast style reminiscent of John Blanche. The scene is bathed in deep reds and grays, evoking an atmosphere that reflects enigmatic beauty. This unique blend meets artwork in the style of Darko M chatzovian, showcasing futuristic architecture with dark tones and intricate details.

Adding cyberpunk into the prompt creates interesting results. Something about the environment.

Ha, ha. I like the last line, clothes from GAP. I am going to use it.

Ok my friends. I feel like I had it with the three fingers and five legs. I decided to dig deeper on this issue and made a collection of key words that are great for removing some unwanted visual effects. These work great depending on the image, so give these a try as you need them. I have the feeling this is list that will keep growing. Worst Quality, Low Quality, Poorly Made Bad 3D, Lousy Bad Realistic, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, deformed bows, missing ear, error, Polydactyly, missing digits, extra digits, simple background, blank background, abstract background, Easy Negative, bad-hands-5, bad and mutated hands, bad hands, missing fingers, multiple limbs, interlocked fingers, ugly fingers, extra digit and hands and fingers and legs and arms, crown braid, deformed fingers, long fingers, comic, muscles, sinewy, bad anatomy, signature, monochrome, text, watermark, duplicate, bad-artist-anime, mature

@Jeff Prince I heard firemen were still at it in the morning. So, I took the original image and used it as the base. Prompt: building in ruins, destruction, surrounded by zombies, apocalypse, dust, debris, broken pavement, firefighters. I had some severe results but this one is PG-13. My guess is now we can get into the action movies as story boarders.

I am always intrigued by the creativity of the facades of Movie Theaters. I think I'll give this AI a go. For better results, create a simple base model to land the camera view. It takes several tries.

I sense a disturbance in the Force

Animate? Nope.

This one has a bit of post production. I think I'll use it as my screen background later.

@VIRTUALENVIRONS That was certainly a challenge. Getting a decent prompt took some time. I had to get help from ChatGPT to learn about some of the key words that would help trigger the deep sea scene. Certainly the creativity level needed to be high because I only had two elements in my file, a crude submarine and a subdivision floor with lots of bumps.

During the testing of this AI, I found that underwater images are not an easy task. The prompt is fighting me a bit even though I described every piece I can think of. Because of the randomness, I got the tanks in different places, fish are easy, caustics are hard. I also found that creativity plays a big roll, the higher the better quality but deviates from the source image. After about 30 something attempts, I think I got a decent concept. Now is your turn.

Zoom in closer so you can read the prompt. The drawing style can change to anything.

The other day, a friend hit me up for some set design ideas (not my field of expertise) – nothing too fancy, just throwing around some concepts. I figured it was the perfect opportunity to give this new AI a whirl. With ChatGPT's help, we quickly brainstormed some decent prompts to get the creative juices flowing. Here's how it went down: started with basic graphics, think lions and sunsets, then imagined them on a small theater stage. Sure, there's tons more that could jazz up the set, but these initial ideas got the ball rolling. How about you? Any cool experiences mixing AI into your creative process?

"Wet wash watercolor sketch" Excellent key words. Thank you

Hello @Grethe Connerth Thank you for your kind comments. Just because you are one of my fav users I made these for you. Hopefully you can crop them and use on your renderings. Show us your work when you are done.

Last batch. These are 2d illustration style.

One more finding. Once the final image is created, the same can be used as a template for consequent images. See more samples.

I found these shapes can be created by combining key words like "Human Figures" and "Turnaround Page" add a white background and you'll be set. I believe the same works for other items. Animals, Trees, etc.

I've been very intrigued by creating concepts of futuristic buildings and full metropolis. AI Visualizer, images from prompts only can create interesting proposals but it all depends on the prompt. I'll start with the first sample.

Here is a new finding, try typing "Monotone oil and ink architectural sketch". The word monotone forces the image to eliminate colors.

With this massing model we can see how at 100% creativity the sketch looks a lot better but it becomes someone else's project. By bring it down to 50% I found a happier compromise.

When you press that "refresh button" behind the scenes is taking a screenshot of the model, pure pixels, that's part of the process to understand, if you take a screenshot of an obscure blob with no edges, creating something from it requires you to type or explain what it is. So, nope, this thing is not smart enough to know automatically what you have on screen is a: kitchen or a skyscraper or a ketchup bottle, it needs some help. A 2d image is valid, a napkin sketch is valid, a massing model is a start, a detailed 3d model helps. I am always on the look out for prompt formulas, I found this recipe that works for architecture, but also applies to other fields.

The images I am posting here are just the few that I felt like I nailed it. Took me more than 20 tries. I found that starting with the creativity slider at 0 sort or matches the lines in the source image (screenshot) but gives no so interesting sketching results, and in many cases adds unwanted heavy lines. Moving the slider to 100% provides super better quality but then it looks nothing like the original model. So, I went down to 60,50,40....but then I thought, since my goal is just to create doodle sketches, no precision is necessary, so raised it up to 60,70 until I got something better.

During my first attempts to create some concepts from thin air, I learned a few things about composing a prompt describing the interior of a gallery with a unique parametric ceiling. I'd like to share some screenshots and final results. (If you try this prompt, try changing the colors)

I thought I'd share here another happy discovery. The prompt: oil ink architecture sketch, triggers some interesting concept images, the colors are more vivid than watercolor. I think may be my go to for future projects.