-Update v1.6
This is Reworked version for try to make it more flexible an powerful.
Give a review is appreciated, and please report where it not work.
Tested with ONLY it on negative, and with other embedding for better compatibility.
Made some sample image with old v1.4 prompt for comparison.
-Update v1.4
reworked for better understanding prompt.
try to make it get clear line/color in cartoon-anime style prompt.
tested with and without some of my other embedding for make it not washing out other embedding.
worked for do better background consistence.
Some sample image made with my old model KKW Ideal and standard DPM++ 2M Karras sampler.
Tips
When use it in negative, and you want to weight it, just use these tips: after weight it, add it again without weight, like
(kkw-new-neg-v1.4:1.8) kkw-new-neg-v1.4
********
If in your model weight it giving bad result, try adding it multiple times without weight.
After many test, i reworked my negative for made a single one that not waste so much prompt and work great for all style you want.
The last 8 image attached are same prompt at different cfg(2,5,8,11,15,20,25,30) to show how this negative work.
Tested on my own model, let me know how work in other model, share result help me to do it better.
Description
-skipped test version v1.1 v1.2 v1.3
-make it work better in prompt understand
-fixed some issue found in older version
FAQ
Comments (5)
thanks !!! really cool!!! do you consider release a LorA version? (can made more different weight? Thanks a lot 馃槏馃グ馃グ馃憤
TY! i'm under testing how make Lora and how it work, need to do some test to understand the training functiion and find my way on how made LoRa.
Dear Devilkkw,
I would like to express my appreciation for your efforts. I am truly amazed by the unique style you've achieved in images #2 and #3.
I have noticed that your images incorporate certain parameters that I'm unable to access, hence modify. These parameters include:
" tome_random: True, tome_stride_x: 2, tome_stride_y: 2, tome_merge_mlp: False, tome_merging_ratio: 0.5, [...] tome_merge_attention: True, tome_maximum_down_sampling: 1, tome_merge_cross_attention: False ".
Could you please enlight me on how to access and modify these parameters? Despite my efforts to find informations, I haven't been successful thus far.
Thank you for your attention. Wishing you all the best!
hi, thank you. the tome is an extension for a1111 you can found here: https://github.com/SLAPaper/a1111-sd-webui-tome . It's archived because last version of a1111 have their own optimization. But i keep it because work great with built-in optimizer. With tome i've boosted generation by 50% of time. I cant reach these generation speed with built-in optimizer so i use both.
@devilkkw聽Thank you very much Sir, I installed it. Kinda complicated, for now I'm just using it with your settings... they work smooth and good with my poor GTX 1050 2GB vram!
All the best, See Ya Sir
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.