Cars with Juggernaut model.
Tried my hand at cars. I used the Juggernaut model. The prompt uses regional prompter extension and looks like this:
> > > at night city, summer, sweaty ADDCOMM > RAW photo, Nikon Z6 II Mirrorless Camera, hyper realism, extremely detailed, 8k uhd, dslr, soft lighting, high quality, film grain ADDBASE > ADDROW > ADDCOL > Aston Martin zeekars, hotrod, LED, lora:zeekars:.7 ADDROW > Negative prompt: JuggernautNegative-neg, transition of shapes, blurry, (((numbers on door))), duplicates, close range angle, crop, illustration, drawing, painting, sketching, render, artwork, 3d, cgi, logo, text, letterbox, 3D, render, video game, anime, cartoon, sketch, caption, subtitle, signature, watermark, username, artist name > >
I use SD upscale and ControlNet Tile for upscaling with 4x\_NMKD-Siax\_200k. zeekars is a Lora.
I hope SDXL will improve in all the small details for mechanical, geometrical forms. At first, the image looks great but when you look closely, panels separation, headlight, tyres look unrealistic...We will see tomorrow!
Simple tasks can take you way more time than needed. For example, I have an old laptop under Bunsenlabs (based on Debian with Openbox). The other day, I wanted to connect a secondary monitor. I wasn't expected the nightmare I had to setup this thing. The layout was totally off with a dead space between the two screens where the cursor disappeared and ArandR was very rough to use. I ended up editing txt file if I remember correctly.
I absolutely love Linux but this kind of thing happen quite regularly to be honest.
I believe you already know it but check CivitAI: https://civitai.com/models/24934/dark-fantasy for example.
Great idea! Which model did you use?
I hope SDXL will bring more realism and coherence to small details likes the shape of the button, knobs or USB ports.
All konyconi loras are fun to be played with! Did you inpaint with Auto or using ControlNet inpaint model?
It’s also pretty cool to listen to a radio program that’s been hand picked by a radio host
So true. Personally, I listen periodically radio paradise.
How to use ControlNet Reference to quickly transfer a style in Auto1111
The reference family of preprocessors in ControlNet allow you to quickly transfer a style from an image in txt2img or img2img mode. I will demonstrate how to use it in txt2img.
-
download this image. I chose the 853x1280 size. We will use it as our ControlNet Reference image.
-
setup your ControlNet tab like this. ControlNet setup If you wonder what is the difference between the reference preprocessors, you can find more info here
\-add a prompt close to the style of your image. Very important, set the CFG to a low value (3,4). Otherwise, your result will look very dark and overcooked. This is my settings: text2img settings
Try to keep the aspect ratio of the original image but do not hesitate to experiment.
- Results: original image Albert Scarlett
I was looking for some info on SDXL on stabilityai website and found this link in the news section. Never heard about it so I wanted to share.
Stable Digest | Stable Foundation | Substack
AI Art News & Culture by the people, for the people. Click to read Stable Digest, by Stable Foundation, a Substack publication with tens of thousands of readers.