Stable Diffusion v1.4 with webui, text to image prompt ‘duck dog crossbreed. duck body with dog head, colorful, vibrant, photo, hdr’. Seed 1452105393, Classifier Free Guidance Scale 6.5, sampling steps 250. Sampler:k_lms. One thing that Stable diffusion is clearly not good at is dog/duck crossbreeds.
Beautiful stripy cat behaving like a tiger, colorful, vibrant, cute, very fluffy, photo
Stable Diffusion v1.4 with webui, text to image prompt ‘beautiful stripy cat behaving like a tiger, colorful, vibrant, cute, very fluffy, photo’. Seed 3013555706, Classifier Free Guidance Scale 2.5, sampling steps 250. Sampler: k_lms. This image has also been fed through the esrgan for a 4 x size. This highlights an interesting point: although you can change the resolution of the images generated by the stable diffusion net, it’s far easier to use another network to upscale the image afterwards. You can see here that this process is highly successful.
Telegraph poles lining a long straight road. Colorful, vivid, photo
Stable Diffusion v1.4 with webui, text to image prompt ‘telegraph poles lining a long straight road. Colorful, vivid, photo’. Seed 48, Classifier Free Guidance Scale 21.5, sampling steps 49. Sampler: DDIM.
Old-Fashioned Yellow Motorcycle
Stable Diffusion v1.4 with webui, text to image prompt ‘old-fashioned yellow motorcycle’. Seed 42. Classifier Free Guidance Scale 15, sampling steps 102. Sampler: k_dpm_2, curated image from thirteen. 704*512 px. It’s interesting that the generator stuck with the yellow theme throughout and this was represented in all the sample images.
Big Ben in the style of Katsushika Hokusai
Stable Diffusion v1.4 with webui, text to image prompt ‘big ben in the style of Katsushika Hokusai’. Seed 42, Classifier Free Guidance Scale 15, sampling steps 53. Sampler: DDIM. dims 512*704 px
Cute, but very smelly dog
Stable Diffusion v1.4 with webui, text to image prompt ‘Cute, but very smelly dog’. Seed 81002952 for the good & 231295628 for the bad, Classifier Free Guidance Scale 7.5 for the good and -37.5 for the bad, sampling steps 50. Sampler: k_lms. This post demonstrates why giving the classifier more scope to wander away from the prompt is not beneficial in most cases!
Snot on a Window
Stable Diffusion v1.4 with webui, text to image prompt ‘SNOT ON A WINDOW’. Seed 2508499346, Classifier Free Guidance Scale 7.5, sampling steps 50. Sampler: k_lms
Tiger submarine
Stable Diffusion v1.4 with webui, text to image prompt ‘tiger submarine’. seed 1, classifier free guidance scale 9, sampling steps 82, sampling method LMS. Curated best and worst results from 50 image samples. Of course, ‘best’ and ‘worst’ is subjective, but this is a great example of the wide range of images that Stable diffusion will generate!
It is only fair (thanks Rob) to consider ‘submarine tiger’ too as the first image is clearly this rather than the original prompt, so let’s see what difference it makes. Spoiler alert – none of the set of fifty images contain any tigers!