The Crochet Pirate Ship image was created using NightCafe AI Image Generator. IMHO NightCafe Studio is one of the best AI image generators for newbies.
Crochet Pirate Ship
The Crochet Pirate Ship is a fun AI text-to-image prompt to create images that look like they were made from wool/yarn in a crochet style.
The primary prompt: “Extremely detailed beautiful enchanted flying pirate ship in space made in crochet, crochet galaxy, crochet planets, colorful yarn threads, photorealism, crochet fantasy landscape, inspired by studio Ghibli, Textured, octane photograph, 4k, gorgeous composition, vibrant triadic colours, 8K resolution 64 megapixels soft focus”
Uses the word “crochet” 4x and that’s supported by the terms “yarn” and “threads”, emphasising that crochet, yarn and threads are important. This is how you make sure an AI-generated image hits a particular theme. If you want crochet to be considered important, REPEAT it multiple times.
This prompt would be easy to adapt to things like a spaceship rather than a pirate ship.
The result is a fun high quality image of a pirate ship with crochet planets and galaxies. If we ran this multiple times, some would be in space.
I copied this prompt from another NightCafe creator and I believe the different styles of Studio Ghibli (anime animation studio) and terms like “4K, 8K resolution, 64 megapixels” are clashing. Studio Ghibli anime is generally not high resolution, (see Studio Ghibli movies like Ponyo) so I suspect the term Studio Ghibli isn’t having much of an impact on this AI prompt. When creating prompts you have to take into account if you add too much of something (like the different resolution terms above) it can override other terms.
AI Image Creation Settings
Stable Diffusion XL 1.0 (SDXL 1.0).
NightCafe Creator model Mysterious XL v4: An SDXL model for fantasy art and Asian culture, by LahIntheFutureland.
AI Image Text Prompts
Primary Text Prompt
“Extremely detailed beautiful enchanted flying pirate ship in space made in crochet, crochet galaxy, crochet planets, colorful yarn threads, photorealism, crochet fantasy landscape, inspired by studio Ghibli, Textured, octane photograph, 4k, gorgeous composition, vibrant triadic colours, 8K resolution 64 megapixels soft focus,”
Weight: 1
Negative Text Prompt
“empty background, Low Rated, Frame, Low Quality, Worst Quality, 3D Render, Plastic, Simplistic, poorly drawn face, mutation, bad anatomy, bad proportions, extra limbs, Liz Gael, out of frame, long neck, unclear, body out of frame”
Weight: -0.7
Stable Diffusion XL has many problems with hands, feet, replicating body parts etc… added to images. This is where the negative prompt helps. By setting a negative number like -0.7 (note the negative sign -) this tells the AI to NOT do these things. The above negative prompt is saying don’t have an empty background, be plastic or simplistic etc…
Other AI Prompt Settings
Initial Resolution: Medium
Runtime: Short
Seed: 3634566090 the seed number adds randomness to the AI image creation process.
Overall Prompt Weight: 75%
Refiner Weight: 10%
Sampling method: K_DPMPP_2M
