My first try with Illustrious XL v2.0.
suggested setting : Euler A, 20step or above, CFG around 5
This model support human language prompting, good with multiple resolution , from low res 768x768 to high res 1536x1536.
It’s support a very high aspect ratio like 1:5 or 5:1.
Suggested quality prompts : masterpiece, best quality, amazing quality, absurdres, extremely aesthetic, newest
Suggested negative prompts : bad quality,worst quality,worst detail,bad, low quality, low details, poorly drawn, bad anatomy, extra fingers, bad hands
All image uploaded by me was generated WITHOUT using any kind of enhancing, it’s mean no HiRes, no upscale, no detailer or other stuff, just a raw output.
Description
my first model with illustrious XL v2.0
FAQ
Comments (7)
Good first model, looking forward to future refinements
👍 ❤️
does low cost model exist on civit?
There is an obvious improvement over the base Illustrious 2.0. Other illustrious loras work as expected. I need to do more testing to find out if it's better than the 1.0 finetunes like WAI. Overall, it's a very promising finetune!
I use the 1.9 Low Cost version on Pixai. Not only is iyt one of the best models but its cheap to use there too. Great job on this!
use VAE？
i have problem upscaling image with this model, it said :
aimdo: src/model-vbar.c:65:WARNING:VBAR 000001A613DF6340: Resident page 0 is ABOVE watermark 0
aimdo: src/model-vbar.c:69:WARNING:VBAR 000001A613DF6340: Page 0 is PINNED
it is done using 4x ultra sharp or its family, but it is okay with 1x skincontrast-superultra, but it is blurry with that model. it is exactly happened when vae encoding.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.