I had fun trying to do this “in camera” without any editing after generation. I ended up using segmentation but after playing around with a lot of different options for what colors to use (trying stone, book, window, painting), I gave up and just made it black and white and still used segmentation.
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.
Here’s with adetailer but putting only the expression part in the positive prompt. Negative prompt still the same as the main image. (confused concerned upset questioning (funny fun amused (cringe (raised eyebrow) shy blush ashamed bruh face), <lora:add_detail:1.2>
Now, probably a good idea to have redhead woman in there or something, but my point is how rapidly you can improve things with very minimal effort. If you’re willing to mess around with adetailer prompts and denoising strength, you can do a lot with faces.
In the comments we will vote on a theme for this coming week for the competition. The comment with a theme that has the most upvotes by the end of the vote in ~48 hours will become the theme for the weekly challenge....
Use the adetailer extension to improve faces. Just turning it on for faces will have a huge improvement. Make sure to turn off the normal “restore faces”.
When you’re happy with a final image, re-generate it with upscaling.
Try using negative embeddings like fastnegative, deepnegative, BadDream, EasyNegative, and maybe negativehand. Don’t have to use all of them, and some work better for some checkpoints and styles than others. Usually I use 2 or 3 together.
Use quality tags in the positive and negative prompt.
The vampire vibe in your original image could definitely be brought back, but I assume it was more of an unintended side-effect of your prompt than intentional.
I just noticed it doesn’t put the literal prompt in the png info. The “dagger (weapon)” needs to be entered as “dagger (weapon)” so that the parenthesis around weapon get sent to CLIP
This is the AI Image Generation Community Challenge post, the theme is Dieselpunk. Comment your submissions on this post. The details of what constitutes dieselpunk can be found in this in depth wikipedia article here: en.wikipedia.org/wiki/Dieselpunk....
Adventures in SDXL (14,000x10,000 zoomable collage) (www.easyzoom.com)
https://lemmy.world/pictrs/image/971bcb41-4e7c-48d3-b857-7d8bdd1ddbfa.jpeg
Adventures in SDXL (Zoomable 14,000 x 10,000) (lemmy.world)
[Community Challenge] Week 2 "Goosebumps Book" (sh.itjust.works)
This is the AI Image Generation Community Challenge post, the theme is:...
Trying to get certain emotions is annoying (sh.itjust.works)
[Community Challenge] Week 2 Theme Vote
In the comments we will vote on a theme for this coming week for the competition. The comment with a theme that has the most upvotes by the end of the vote in ~48 hours will become the theme for the weekly challenge....
Ramen time (files.catbox.moe)
A golem. (lemmy.world)
Tried to Make a Character Portrait for D&D (sh.itjust.works)
Model: civitai.com/models/4384?modelVersionId=109123...
[Community Challenge] Dieselpunk (i.imgur.com)
This is the AI Image Generation Community Challenge post, the theme is Dieselpunk. Comment your submissions on this post. The details of what constitutes dieselpunk can be found in this in depth wikipedia article here: en.wikipedia.org/wiki/Dieselpunk....
Relative Humidity (i.imgur.com)
Bridge and clouds (i.imgur.com)
Photo from anthropologist Monty Pytorch, the first person to ever live among the Neanderthals. (i.imgur.com)