This is the AI Image Generation Community Challenge post, the theme is:

Goosebumps Book

Come up with a book title and generate cover art in the style.

Suggested here by Hypnotized@lemm.ee: https://sh.itjust.works/comment/1083201

Comment your submissions on this post.

You can submit your AI generated images to be voted on for the contest by commenting and embedding your images.

Please use "![](imgurl)" format to embed the image in the comment so users don’t have to go to other websites.

You don’t have to upload the image to sh.itjust.works specifically, and can use imgur links and other webhosting sites as well.

Strict simple rules to make this more enjoyable for everyone:

Contest will begin immediately when this post is made and will end the following Friday at 1pm EDT

One comment per user

3 images maximum

Must follow this community’s and sh.itjust.works rules

No links to other websites, must be embedded and viewable here

The top 3 winners are the top 3 root comments with the most upvotes

The top 3 winners (9 images total potentially) will be featured as a pinned post as the contest winning images with user names

I just typed “goosebumps book” into DALL-E for this post’s image

  • wgty@lemmy.worldEnglish
    3·
    1 year ago

    Segmentation controlnet with an image of the cover template with different parts being different colors as the input. The segmentation controlnet makes Stablediffusion treats different colors as different things, so it keeps each part distinct. If you use colors that aren’t in the actual color reference chart, it just sorta improvises, so I used black and white. On one I used the color that corresponds to painting,picture for the area inside the “frame” where the actual art is. Since I was doing it all in one generation with one prompt I just sorta had to accept what it gave me for the colors and textures of the text and borders.