画質 高画質

In honor of my T400 for Footsteps event!

51 158

盗んだ呪文で走り出す〜♪
三⊂( ^ω^)⊃
この一枚、雰囲気は文句ないんだけど、女の子がちっさい!
Steps上げて粘れば良い作品が出来そうかも
https://t.co/3FdljYdYXQ

2 12

Its my stepsister's birthday today so why not get a AI art on HashAxis so we can get her a cake 🎂

Link: https://t.co/Yd5G0fa7Nj

0 4

私などのオリジナリティのない呪文に需要があるかは分かりませんが、せっかくなのでこの子の召喚用の呪文を置いておきますので、良ければ見てやってください。

Steps28のScale8、1枚目がPromptで2枚目がnegativeでございます。

0 11

haha funny cult leader steps on you ✨

https://t.co/opTU3K5Sx1

7 79

1024×1024 steps50連打して高額突っ込んできた。
タイトル「キャバ嬢」にしようか悩んだけどギリギリで踏みとどまった。

https://t.co/7Vqdjgoy51


0 8

got official DPMSolver++ sampler working on Mac.
today, Cheng Lu added a trick to improve performance on <15 steps. probably k-diffusion doesn't have this yet.
dynthresh only works on pixel space; remains an unsolved problem on latents.
https://t.co/22rDBzDWiW

1 40

習作:水彩、masterpiece
Steps:28,Scale:11
k_euler
Seed:85889117

1枚目のSeedで、以下の呪文をそれぞれ追加
2枚目:ukiyoe
3枚目:utagawa
4枚目:Monet

ここから分かる効果範囲
ukiyoeは人物と背景、utagawaは人物、Monetはご覧のとおり。

9 47

At 11k steps there's very minimal similarity to miata; conversely, it's very noticeable with realistic art: I didn't highlight the eyes in the prompt at all!
I'm now positive that Google is indeed progressively lowering Colab limits with usage.
https://t.co/FIeOpnIaAy

0 0

初音ミク指定はしてないけど
初音ミク風の子が出た

DDIM
Add quality tags:off
steps:28
Scale6.5
PromptはALTに記載




12 65

Steps50だとAnlas25も食われる高解像度版スクエア Scaleは上げたり下げたりはしとる 音楽ジャケットみたいで良いわね 

0 1

Attempted to do pixel art today for the first time, of course with vex. Very unsure on the end result but baby steps and all

0 13

Two pairs of footsteps became one.
Rolan turned around.

Kian looked up.

-
-
-
guys. this line knocked me on my ass. felt that one for a few days ow

12 92

Initial Results using 10 steps before further amplification.

0 2

28k steps is OK and 20k is very close as well, so I'll consider the sketch one to be working just fine and move on to do miata.
Same folder as before:
https://t.co/3n45LiqpQc
https://t.co/TXTDZDS6sw

2 3

with DPM-Solver++(2M) sampler, we get coherent images in 5 sampler steps!
and these aren't Heun steps (where n steps = 2n-1 model calls), this is just 5 model calls! less than 3.5 secs on Mac!
Katherine released this implementation yesterday in k-diffusion — great work as usual!

21 156

As per recommendation, here are three practical steps – all of which involve investing more in people – that countries can take to improve Social Inclusion and Economic Growth simultaneously.

https://t.co/uZOWNjaYL2 rt

19 13