The Adorable Sloth image was created using NightCafe AI Image Generator. IMHO NightCafe Studio is one of the best AI image generators for newbies.
Adorable Sloth
The Adorable Sloth AI image has a general watercolor feel to it, but it’s also got elements of cubist painting, Neo-Cubism, layered overlapping geometry due to using contrasting styles.
The great thing about AI image creation is by mixing various styles and artists in the prompts you can get something unique. You’ll see in the AI prompts used below the only artist mentioned is William Turner. Take a few minutes to look through William Turner’s art via a Google image search and you’ll see the Adorable Sloth image doesn’t look anything like one of his art pieces.
You will note in the prompts below the replication of some terms:
2x Adorable sloth
2x watercolor
Terms meaning similar things:
geometry, 2x geometric
By repeating important phrases/terms, those tend to be treated as important by the AI. You can also add brackets around phrases/terms as well to achieve the same result. (Adorable sloth) is the same as 2x Adorable sloth. ((Adorable sloth)) is the same as 3x Adorable sloth.
AI Image Creation Settings
Stable Diffusion XL 1.0 (SDXL 1.0).
NightCafe Creator model Starlight XL: An SDXL model designed for creating stunning concept art and illustrations. by chillpixel.
AI Image Text Prompts
Primary Text Prompt
“Adorable sloth long exposure Digital watercolor Illustration of a beautiful flower meadow fantasy Adorable sloth, by William Turner, Stylized watercolor art, Soft-edges, Intricate, Complex contrast, HDR, soft Cinematic Volumetric lighting, pastel colours, perfect wide long shot visual masterpiece”
Weight: 1
Secondary Text Prompt
“cubist painting, Neo-Cubism, layered overlapping geometry, art deco painting, Dribbble, geometric fauvism, layered geometric vector art, maximalism; V-Ray, Unreal Engine 5, angular oil painting, DeviantArt”
Weight: 0.9
Negative Text Prompt
“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”
Weight: -0.3
Stable Diffusion XL has many problems with hands, feet, signatures etc… added to images. This is where the negative prompt helps. By setting a negative number like -0.3 (note the negative sign -) this tells the AI to NOT do these things. So the above negative prompt is saying don’t create messed up hands, feet etc…
Other AI Prompt Settings
Initial Resolution: Medium
Runtime: Short
Seed: 2348946024 the seed number adds randomness to the AI image creation process.
Overall Prompt Weight: 75%
Refiner Weight: 50%
Sampling method: K_DPMPP_2M
