{"id":446,"date":"2024-05-20T13:45:12","date_gmt":"2024-05-20T17:45:12","guid":{"rendered":"https:\/\/kryptech.name\/site\/?p=446"},"modified":"2024-05-20T13:45:14","modified_gmt":"2024-05-20T17:45:14","slug":"stable-diffusion-generation-widescreen-grungy-factory","status":"publish","type":"post","link":"https:\/\/kryptech.name\/site\/index.php\/stable-diffusion-generation-widescreen-grungy-factory\/","title":{"rendered":"Stable Diffusion Generation: Widescreen Grungy Factory"},"content":{"rendered":"\n

I like the aesthetic of vast industrial spaces filled with pipes and wires and rust, so I made a wide image designed to span both my 1920 x 1080 monitors. My meagre GTX-970 can’t manage such a large image so I generate a bunch of smaller images, find one I like, and then extend it and upscale.<\/p>\n\n\n\n

(I’ve only included the main steps below – I often use inpainting to refine various parts of the image along the way.)<\/p>\n\n\n\n

Here’s the initial image I chose, with this prompt:<\/p>\n\n\n\n

interior of a huge industrial factory, (hundreds of machines:1.1), massive gears and mechanisms, pipes, tubes, wires, gritty, rusty, dirty, grim, neon lighting, (cyberpunk:1.1)<\/em><\/p>\n\n\n\n

I used 8 steps and DPM++ SDE for the sampler.<\/p>\n\n\n\n

\"\"<\/a>
Starter image<\/figcaption><\/figure><\/div>\n\n\n\n

I liked the variety of things, and particularly the machine on stands near the middle and the large tank on the right side. Now I spent some more steps on that to improve the quality, using img2img. I used the same sampler but with 30 steps, and a denoising of 0.4 to generally keep the structure but allow the detail to be rebuilt.<\/p>\n\n\n\n

\"\"<\/a>
Ran through img2img<\/figcaption><\/figure>\n\n\n\n

The quality is improved – more crisp. Next I used outpainting to extend the image left and right.<\/p>\n\n\n\n

\"\"<\/a>
Extended horizontally to 1408 px <\/figcaption><\/figure>\n\n\n\n

The glowing doorframe is a nice cyberpunk touch. The right edge gives the feeling of the hazy outdoors with industrial smog. The boxes in the foreground right are off, though, so that needed help. I inpainted that area with this prompt:<\/p>\n\n\n\n

interior of a huge industrial factory, (metal boxes:1.2) of broken machines, gritty, rusty, dirty, grim, concrete<\/em><\/p>\n\n\n\n

\"\"<\/a>
Fixed boxes<\/figcaption><\/figure>\n\n\n\n

Much better! Time to outpaint to extend further.<\/p>\n\n\n\n

\"\"<\/a>
Extended horizontally to 1792 px<\/figcaption><\/figure>\n\n\n\n

A mysterious box with a glowing symbol – noice! But it also looks a bit janky. Rather than a symbol, I preferred an opening\/window to something going on inside the box. Inpaint it! Here is the prompt:<\/p>\n\n\n\n

interior of a huge industrial factory, glowing furnace, high temperature, gritty, rusty, dirty, grim, concrete, metal, glass<\/em><\/p>\n\n\n\n

\"\"<\/a>
Refine box on the bottom left<\/figcaption><\/figure>\n\n\n\n

That’s better. Time to extend to the full width necessary: 1920 x 512 pixels. I generated a bunch of outpaintings and settled on this one.<\/p>\n\n\n\n

\"\"<\/a>
Extended horizontally to 1920 px<\/figcaption><\/figure>\n\n\n\n

Now that the ratio is basically correct, it’s time to upscale. I used ControlNet with “tile_resample” and Ultimate SD upscale with 4x-UltraSharp to preserve the structure. It was 30 steps with the DPM++ SDE sampler, CFG of 7, and a denoising strength of 0.5.<\/p>\n\n\n\n

\"\"<\/a>
Upscaled to 3840 x 1080 px<\/figcaption><\/figure>\n\n\n\n

I was very pleased with the result. A few areas could use some help. The glowing doorway is eye-catching so I wanted that to be more interesting. The large tank on the right side with the cyan writing could be improved too. Lastly, I wanted the far right side to be more outdoor than interior and for the reflections to be more consistent. So I inpainted each of those.<\/p>\n\n\n\n

\"\"<\/a>
Inpainted elements for interest, detail, and consistency<\/figcaption><\/figure>\n\n\n\n

The final picture is one of my favourite Stable Diffusion generations yet.<\/p>\n","protected":false},"excerpt":{"rendered":"

I like the aesthetic of vast industrial spaces filled with pipes and wires and rust, so I made a wide image designed to span both my 1920 x 1080 monitors. My meagre GTX-970 can’t manage such a large image so I generate a bunch of smaller images, find one I like, and then extend it …read more<\/a><\/p>\n","protected":false},"author":2,"featured_media":454,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/posts\/446"}],"collection":[{"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/comments?post=446"}],"version-history":[{"count":2,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/posts\/446\/revisions"}],"predecessor-version":[{"id":458,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/posts\/446\/revisions\/458"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/media\/454"}],"wp:attachment":[{"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/media?parent=446"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/categories?post=446"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kryptech.name\/site\/index.php\/wp-json\/wp\/v2\/tags?post=446"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}