diffuseのTwitterイラスト検索結果。 648 件中 5ページ目
Kohyaさん配布のGen img diffusersをV7にアップデートしました。それに伴いpython仮想環境も3.10にアップデートしたのでxformersで高速化できそうです。
@King_PRomulus @ArtvisionNFT Prophecy of the Muse | Urania 💜
With touch of majesty diffused her soul.
https://t.co/jDdg5LnyKb
#KingRomulusArtPick
Thank you for the opportunity to share!
Good night fam. This has been another long and productive day. Tomorrow will be even more fun. Is anyone at all interested in source code for these? It's @huggingface diffusers + my library that does reinterpretation of the latent space.
"cant wait to put an emission map on him!"
his fucking diffuse map:
Stable Diffusion 2.1 (base) is also supported by default in Doohickey (and diffusers in general!)
set the model name to "stabilityai/stable-diffusion-2-1-base" and go ham https://t.co/iKHHzpPG0s
The new Stable Diffusion 2.1 models are now available in diffusers 🎉
Make sure to install from main to use the 768 model. https://t.co/yJcRvSVdVY
After 15 hours of test, I can dreambooth with SD2 768 using shivam!
1) Follow @DevDminGod tuto: https://t.co/7kGax5zz5M
2) upgrade diffusers to the latest
1/2
768x768,2000x2[step]追加学習後。
だいぶうまくなったなぁ・・・。一発生成できるとweb uiのHighres-fixみらいなオプションなしでできるからDiffusersで扱いやすくてよい。あと上田しゃんがちゃんと生成されるの感動する・・・。着ぐるみ多いからAIくんも大変だろうに・・。
Latest sales
diffused miniPod ..., 0.60 ERC20 ($765)
Confluence #201, 0.11 ETH ($140)
BrainDrops #5000488, 0.10 ETH ($134)
#braindrops https://t.co/JE5gFZC0q8
@magifactory @KaliYuga_ai I tried 512 and 728 training.
With 512, I have not tan solid output but results are very bad. I tried 3K steps and 11K and result are awful.
Example with v2 - 512 at 11K training steps (left) (with diffusers)
old training with v1.5 (right) (with shivam repo)
Petit #Goku SSJ4 #CHIBI qui traînait dans le PC.
J'ai une petite poignée de Fanart a diffuser qui trainent 😉👍
#DragonBall #DragonBallGT
Huggingfaceで公開されている DiffusersのモデルEimisAnimeDiffusion_1.0v を使ってみた。
Anything3.0と比べると服の装飾などがより細かくなりやすい(気がする)
服装にこだわりたい人にオススメかも？
#stablediffusion #AIイラスト
https://t.co/1CfpPgb7Hy
"bright psychedelic photo of pink floyd and frank zappa tripping on lsd, diffuse lighting, fantasy, intricate, elegant, highly detailed, life..." - made with @NightCafeStudio
https://t.co/FGsJkq4ZV0
#aiart #nightcafe #digitalart https://t.co/FGsJkq4ZV0
@izumisatoshi05 素のsd2.0 diffusers版で hatsune miku と kagamin rin 試してみました
…ちょっと出力違い過ぎて、設定ミスったかなとかも思いつつ参考になれば・-・
やっと、
#StableDiffusion 1.5でOutPaintingを実装し左右にループする横長画像を生成。
形状破綻も少なく超解像前だけど結構繊細になったような…
備忘録
diffusers 0.7.2
runwayml/stable-diffusion-v1-5
runwayml/stable-diffusion-inpainting
What happens when a detective, a dark elf king, a lounge singer and a kitsune try to diffuse a bomb?
Idk either but let’s find out together! In an hour we go live with @senpaihinotama @JazzyTheSmooth1 and @ShonenVR playing Keep Talking and Nobody Explodes!