@SORAY_AI

Creative Writer bringing dreams to life with AI🩵 Making anime content for shoujotome fans🩷 Proud Creator Partner🌟 https://xitter.cf/t.co/KuIiUYR72L

 A Magical AI Dream
sorayai.dreamgarden.workers.dev/
Joined October 2021
  • Tweets5K
  • Following2.2K
  • Followers2.7K
2.5KMedia
Pinned Tweet
SORAY-AI@SORAY_AI3h
This phantom thief has come to steal the world's favorite queen: you! He'll stop at nothing to claim your heart...♥️ #sorayai_fantasy Made with Flova #flovaai #flovacpp @Flovaai
4
198
Flova's new 1.5 upgrade is a huge improvement, I highly encourage everyone to check it out~ making my next music video with it right now!!
FlovaAI
@Flovaai13h
One project. More than one task. One project, multiple conversations, more creative freedom! - With Flova 1.5, run independent sessions for different creative goals - Explore ideas in different directions with shared project context - Switch conversations anytime and pick up where you left off ✨Turn ideas into videos, your way!
1
69
working on something fun~ #sorayai_fantasy
5
115
Found a video I never posted, realized I had to share it right away~ Angel can be sexy too....!! 🔥💛 they just have different flavors hehe #sorayai_fantasy
7
148
School AUs are always so fun and cute!!! I had this idea yesterday so I made a few clips. Working on the next MV too. Hopefully it will be done soon! have a nice sunday🩵 #sorayai_fantasy
13
939
since this is his Halloween costume of course I had to participate! #sorayai_fantasy #仮面男子を供給せよ
9
673
I live for the sugar and the spice🩵 He's so gentle and sweet. don't we all want a man like this? #sorayai_fantasy
1
19
1,199
SORAY-AI retweeted
いのり
@lnkiaiOct 24
立ち絵1枚からVTuberモデルを作ってみました！！🎉 開発中のVTuber制作キットで、パーツ分けから組み立て、モーションまで再現できるようになりました！ 誰でも使えるように、オープンソースでの公開を目指しています！👇️
いのり
@lnkiaiOct 23
VTuber制作キットの開発とは思えないほど、研究データが集まった！！ 立ち絵のレイヤー分けから、モーションの揺れ方の検証までワークフローを作りました！ ClaudeとCodexを走らせて、5時間ほど研究してもらっています👇️
17
197
62
1,570
214,550
it's almost Halloween🎃🪄 #AIart
11
781
Entry #3: Neon Phantom Masquerade I wanted to see how their neon versions would look in 3D!!! They came out so amazing!!! #TripoHalloween #CharakuruHalloween #Tripoハロウィンフェス #きゃらくるハロウィン @tripoai @TripoAI_Japan
1
8
753
きゃらくるで表情を作れるようになりました！ 表情作成タブからワンボタンで作成できます！ AIエージェントがめっちゃ頑張って作ってくれます！ キット内の独自ツール（？）を駆使して作ります。 v1.1.0をリリース済みです！ 最新リリースよりアップデートをお願いいたします。
16
56
18
425
26,868
Party's Over... ...or is it only just beginning? #sorayai_fantasy @wavespeed_ai @WaveSpeedCPP
11
978
Wanna make your own neon fantasy? Check out my @PixVerse canvas :3 you can make music too! app.pixverse.ai/canvas/proje… #PixverseCPP
7
885
Tango🎵 #sorayai_fantasy @PixVerse #pixversecpp
1
8
847
Neon Moon Witch🌙 @PixVerse #PixverseCPP
10
732
Second Entry: Crimson Domino🌹 I really like this Halloween outfit cause I think Masquerades are awesome! (MMD motion // Persona Dancing All Night: Mass Destruction) #TripoHalloween #CharakuruHalloween #Tripoハロウィンフェス #きゃらくるハロウィン @tripoai @TripoAI_Japan
2
11
750
looking forward to trying Kling 4. I'm curious to compare it to Wan 3 and Seedance 2.5!! Love that we have so many options
WaveSpeedAI
@wavespeed_aiOct 22
Kling 4.0 just landed on WaveSpeed! - Smoother motion, even in high-speed scenes - Up to 30s of continuous storytelling - Up to 15 references + 10 keyframes - More precise camera moves & cinematic shots Less fighting the prompt. More calling the shots. Ready to create?
1
2
493
Kling 4.0 just landed on WaveSpeed! - Smoother motion, even in high-speed scenes - Up to 30s of continuous storytelling - Up to 15 references + 10 keyframes - More precise camera moves & cinematic shots Less fighting the prompt. More calling the shots. Ready to create?
42
26
13
94
6,226
🚨 Confirmed LiteLLM PyPI package compromise… again. Will update details at: flatt.tech/research/posts/li…

Software Supply Chain Attack on LiteLLM: Overview and Response Guidance

Note) This post is a direct translation of this post . On October 21, 2026, malicious code was injected into the PyPI package litellm. This article goes into detail on this malicious package based on...

flatt.tech
2
14
6
43
14,128
SORAY-AI retweeted
fal
@falOct 21
Kling 4.0 is now live on fal. A next-generation native multimodal video model with improved stability for complex motion, stronger reference consistency across characters and scenes, and more precise control over cinematic storytelling. Available exclusively through the fal UX and fal Agent. API access coming soon.
39
39
19
570
74,108
Load more