Following the Artist study done using SDXL 1.0, I started exploring what are the other items that could be studied to see the standard result produced by SDXL model. Of course the art is expressed via different mediums such as paint, water color, digital etc. So I explored the internet looking for the typical list of mediums and also consulted ChatGPT which proved very useful as it saves you lot of time googling things.
So I gathered 211 Art Mediums that art is typically expressed in and started to build my list which I would run through Stable Diffusion XL. After I few experiments I ended up with the below settings for this study. SDXL Refiner was also used to add some details and sharpness to the images produced.
Prompt: <art medium>, portrait of a beautiful woman Negative prompt: Deformed, blurry, cropped, low-res, blur, vignette, out of shot, out of focus, gaussian, grainy, noisy, text, writing, watermark, logo, over saturation, open mouth Steps: 30, Sampler: Euler a, CFG scale: 8.5, Seed: <random>, Size: 1024x1024, Model hash: 31e35c80fc, Model: sd_xl_base_1.0, Refiner: sd_xl_refiner_1.0 [7440042bbd], Refiner switch at: 0.9, Version: v1.6.0-RC-1-gc8c73eae
The result of 200 different mediums is below for you to explore at your leisure. Let me know if was of any use to you, or if you want an other art mediums added to the list.
Offline version of this Study
As many asked for with the SDXL Artist Study to get the images offline so they can explore at their leisure, I have preamted this. As many of you have supported the work I’m doing here on this site. You can download the offline version of the SDXL Art Medium at a nominal fee of $2.