Steve Gilham’s interview

Meet Steve Gilham, a retired software engineer and Gentleman of leisure whose enchanting art is as heartfelt as it is imaginative. Living with his beloved cats for company, Steve has found solace and inspiration in creating surreal, bittersweet worlds that reflect both his passions and his profound loss. A widower after nearly 40 years of marriage, his art is a deeply personal tribute to love, memory, and the passage of time.

Steve’s creations transport us to enchanted realms bathed in the glowing hues of sunsets and sunrises. His skies—vibrant and ethereal—blend reality with fantasy, suggesting contemplative moments caught between time and space. Often, we find a lone female figure wandering through these magical landscapes, dressed in vintage clothing, as though on a timeless journey. These figures, with faces sometimes left unseen, feel like explorers of mystical dimensions, embodying themes of melancholy, departure, and solitude.

Through his work, Steve weaves a poignant narrative of memory and love, commemorating his late wife as a spiritual presence in his art. Whether traveling through tunnels, passages, or desolate cityscapes, his characters inhabit spaces that juxtapose old-fashioned charm with modern desolation, evoking nostalgia and a sense of timelessness.

The dreamlike quality of Steve’s art extends to his love for anime-inspired aesthetics, where historical and fantastical elements intertwine seamlessly. His use of light and color creates an otherworldly ambiance, while his compositions explore the mysteries of time, spirituality, and the human experience.

Steve’s art is not just beautiful—it’s deeply touching. It invites us to reflect on our own journeys through love, loss, and imagination.

Read on as we delve deeper into Steve Gilham’s world, where he shares the inspirations behind his art, his creative process, and how each piece tells a story of memory and wonder. It’s an honor to feature him in this interview.

Let’s discover Steve Gilham together.

The sunset window

Without getting too personal, can you tell us a bit about yourself?:

I'm a retired software engineer, with the accompanying geekish habits and hobbies, widowed after almost 40 years of marriage, and now living with cats for company.

Could you please tell us which country you live in?:

England; and having studied at Cambridge, never saw the need to move very far away from there.

What led you to begin working with AI imagery?:

In my student days, in the late '70s, I'd written some SF and fantasy stories; the advent of generative art seemed an opportunity to try to illustrate them.

What AI tools do you use?:

These days, mostly the Bing interface to DALL-E3 as the most artistically sensitive and convenient, but I still use SD15 and SDXL locally, and keep Remix, Grok and Gemini for alternative takes, mostly in prompt challenges.

What inspires you?:

Generally, I get ideas by free-associating from things I've seen or read that day, but also calling back to themes and motifs from my old writings and RPG settings; but there's also an analytic side, seeing effects done and trying to reproduce them, often re-using old test subject prompts.

QT Silhouette

(One of @revelinai’s favorite images by Steve Gilham)

In which other medium, if any, do you practice art?:

In my teens, I did some pen and paper drawing but never really got anywhere with it; since then, on and off, I've written fiction, as it's easier for me to paint a picture with words than in visual media.

Would you consider AI-generated art true art?:

Yes, for the same reasons as for conventional digital art; indeed, if used as a "PhotoShop filter" pass, where tools permit, over a digital image, it does become digital art.

Even in the pure text plus random number gacha (a Pseudo-Random Number Generator, with either your User ID as the seed or in more extreme cases, the server time as the seed), though, the artist, the prompter, will still show through in the choices of style and subject, and selection of results to publish.

Please share one or a few of your favorite images with us.:

A few of the pieces that stick in my mind:

A ray of sunshine

The memory of that summer

Asuka the Martyr

Playing in the ruins

The wrong alley

Do you title your AI-generated art? If you do, what inspires you to come up with these titles?:

For challenges, rarely; for stand-alone pieces, I let the picture speak to me, and if it doesn't, I don't post it.

When do you tend to be the most productive, and do you work in long sessions or short bursts?:

I need to get into the groove to let go and create, but I equally don't want to take up the whole day. Usually I spend 2-3 hours in the late afternoon/early evening, starting with challenges I've bookmarked to get the juices flowing, then going wild.

Giant

What type of prompts do you prefer: text or AI-generated descriptions through fed images?:

Text, though some of that can be wetware-generated descriptions of images - keeps the brain active and is a reason to learn odd bits of, e.g., architectural terminology.

When prompting with text, do you write simple text-based prompts or complex ones?:

It varies. Art-style will usually take 10-20 tokens (vintage photograph styles going down to 5 or fewer); the subject may be a few words or dozens, depending onwhat I'm doing. The main discipline is the Bing interface 480 character prompt limit.

Do you think text-based prompts should be shared within the AI art community?:

Prompt in this context I understand to mean the art-style part, not the objects in the scene, and I'd say "voluntary but encouraged,” with the understanding that different engines make wildly different interpretations of the same prompt - see, for example, the following style rendered by some common ones:

https://x.com/stevegilham1/status/1859996075698081970

What is the most unconventional method you have used to create an image?:

For one of my favourite below - starting with a pose from JustSketchMe, making a collage background to put the figure in, roughly colouring it, then image to image as filter, and several iterations of collage and inpainting until done.

That was hard work, at the edges of my conventional digital art skill; but with SD15 even as it stood 18 months ago, it covered up my limitations.

How many images you have generated using AI technology?:

Counting the files in my archive directory, around 100,000 - the ones that aren't images I generated, the disasters from my earliest attempts that I discarded, and the ones eaten by the Bing dog, probably canceling out.

Exit into Day

Please share your X (Twitter) handle with us.:

@stevegilham1

Tell us a bit about your X handle and X username.:

It's just my name; the 1 is because I'd lost the password to my first sign up in 2012, and the email I would have used no longer worked when I returned in 2019.

How many X followers do you currently have?:

Closer to 1600 than 1500, with the usual daily fluctuations.

How many X accounts do you currently follow?:

Right now, 570, but a number have gone dormant after promising starts.

How long have you been on X (Twitter)?:

Ignoring the long ago neglected sign-up, since the start of 2019, initially to promote my open-source hobby work.

Walk on the wild side

Is there any other online platform where we can view all of your previous work apart from X?:

Only the tip of the iceberg is online at all, and of those, the vast majority are on 𝕏. Most of the rest are illustrating my fiction on my website, then there are a few on my blog, and a handful in the fan art and avatar threads on the EvaGeeks forums.

In this world of cryptocurrencies and non-fungible tokens (NFTs), are you currently selling your digital art on any platform? If so, which platform are you using?:

No, this is all hobby play in retirement.

Are you selling tangible AI-generated artwork, such as high-quality prints like Giclée prints?:

No, for the same reason.

Could you suggest some AI artists you like that we could follow?:

Kaoru Yamada (@kaoru_creation) was the first whose work really wowed me, but others whose work I always look forward to include:

Is there anything else you would like to add or share with the AI community?:

The fact that we can do this thing, however imperfectly, of turning our word pictures or evocations of moods into actual pictures is not something I'd ever expected; this is all so much fun unlooked for.