Sudakshina | Artist | AI (@magicatastrophe) header
Sudakshina | Artist | AI (@magicatastrophe) profile picture

Artist + Notion lover Trying Google AI for 30 days (and probably breaking it) 😅 Sharing tiny experiments Shop templates here - https://nitter.cf/t.co/tmdXDJtwsu

🇴🇲|🇨🇦|🇮🇳
Joined January 2014
Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)Photo by Sudakshina | Artist | AI (@magicatastrophe)
She restores damaged broadcasts for a living. Some of them arrive as recipes. Cook it right - a world opens. Two minutes. Then it's gone. Every world contains the same number. 108. She thought she was finding them. She wasn't. LOST FREQUENCY - AI series pitch trailer Created for @runwayml Big Pitch Contest #RunwayBigPitchContest #Runway #AIFilmmaking #LostFrequency
1
1
9
474
Sudakshina | Artist | AI retweeted
My humble advice for growing on socials as an AI creator: • Find your own style • Show up daily, no days off • Keep improving, don't focus on one success • Master 3–4 tools, but stay flexible • Invest in yourself first, get rewarded later • Think outside the box
42
24
3
410
14,347
Experimenting with @magnific this month. Loving the retouch and recreate options they provide.
2
95
Sudakshina | Artist | AI retweeted
卧槽!兄弟姐妹们,想用 Opus 5.5 做视频,一定要收藏这 8 个 GitHub 仓库。 1. awesome-opus5-5-videos(约 7100 star) 目前最大的爆款视频合集,每条都附上了背后的提示词。 github.com/yihui-dev/awesome… 2. lemo-opuscar(约 4400 star) 一个 Claude Code skill,装上之后挑一种风格,就能做出纯代码短片,51 种风格随便选。 github.com/lemomo-ai/lemo-op… 3. pdoom-video(约 3000 star) 一支歌词卡拉 OK MV 的完整工程,本地就能渲出 4K60。 github.com/mexicat/pdoom-vid… 4. PDoomVideo(约 2300 star) 同一首歌的另一支 MV 源码,和第 3 个对照着拆,很有意思。 github.com/JohnHeibel/PDoomV… 5. mg-styles-15(约 1400 star) 15 种 MG 动效风格,成片、提示词、源码全都给。 github.com/Vincentwei1021/mg… 6. ClaudeAnimationBase(约 1300 star) 手绘卡通角色动画的起步包,自带 31 种表情。 github.com/JohnHeibel/Claude… 7. awesome-claude-5-5-videos(约 560 star) 视频工作流合集,每个案例都标了出处,Opus 的就有 301 个。 github.com/athemeroy/awesome… 8. opus-video-prompts(约 510 star) 中文案例,配上能直接复制的提示词。 github.com/joeseesun/opus-vi…
143
1,110
80
9,186
820,972
Sudakshina | Artist | AI retweeted
Opus 5.5 + /anatomy skill is f*cking insane for motion design but... add /anatomy-reveal to turn Claude into premier motion design studio • Real-size 3D models from a photo or name • Motion-blurred reveal films, 1:1 to 16:9 • Exploded views you can take apart send skills your Claude: > typingmind.com/skills/annngu… > skills.wheresryan.sh/anatomy
25
71
2
834
47,052
I typed 9 words into Gemini 4 Argon: "Make a launch video for a protein curd brand." I didn't just get a prompt response or a static storyboard. It acted as creative director, sound designer, and video editor, producing a complete 1080p commercial with original audio, motion graphics, and full brand strategy.
2
2
159
What? Wow!
$52M seed round. 15M+ users. But this is what we're most proud of yet. Introducing Drama 3: the most emotive and controllable TTS model in the world And yes, it's open-weight. You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence. Uncle Roger was impressed too. Try it here: s.fish.audio/rqh0l8 Comment “DRAMA” within the next 48 hours for 1 month free. If you're an enterprise your first month is on us: s.fish.audio/qz9r0t
2
30
Trying to learn some Claude code @AnthropicAI today. I am an Artist and have no idea about code but am super interested in Design + Tech. Trying to learn from whatever I can. If someone can suggest what to learn and from where - open to some advice :)
1
29
10-second title study: RAKING LIGHT One object: a train ticket. One rule: words exist only as dents in the paper, and only low light reveals them. @Procreate lettering → @ChatGPT texture → @Blender lighting → Resolve. ~3 hours.
1
33
Sudakshina | Artist | AI retweeted
Don't let your perfection become an excuse for not getting started ✏️
23
108
5
1,016
29,491
Sudakshina | Artist | AI retweeted
We're giving away 6,000,000 credits. One mission: create. Fuel your next AI film with PixLight. Start creating. Start your story. Follow + RT + Reply = 150 Creds & Access to 6M Creds in DMs(72H ONLY)
564
525
25
577
24,393
Tried out some prompts by @xiaoxiaodong and I must say the results are absolutely beautiful!! Thank you so much for sharing!! Here are some images I generated with my own photos
🤖 Made with AI
1
1,518
Happy independence Day! 🇮🇳
🤖 Made with AI
32
One Drop 💧 Archive. Made some BTS of all my AI work. Not sure if this is worth it, but I am determined to show a little bit of the process behind all my AI projects.
47
MEET THE FLOCK. Four birds from my brief NFT era, created for a collaboration between stc and Aleph Zero. The series went on to win, which still feels rather lovely. 🥰 Bringing this very well-dressed flock back out of the archive because they deserved another flight. #illustration @procreate
1
1
93
Cinch Paper Clips - the archive 📎🚀 A little look at everything behind the final @runwayml contest film.
1
42
Sudakshina | Artist | AI retweeted
One of the coolest AI animations I've seen. Building this workflow now.
Someone made this hand-painted style video entirely with AI. Once the models are good enough, they stop being the bottleneck. Anyone can generate a pretty frame. What separates the work is taste.
44
156
18
2,901
240,723
A little fun experiment from my mums DIY planter
🤖 Made with AI
1
1
52
AI-assisted visual development and a lightweight Figma review workflow.
52