Jin

...

[Seyi @seyii___]

Quick exploration. Moving images along paths. Made with #threejs #tsl #webgpu.

[JB @Bhumimov]

Pov : If @figma hire me for launch video

[FHILY👑 @Oluwaphilemon1]

I recorded a 44-min tutorial on how to prompt CLAUDE for ui

[Praveen Kumar @praveenisomer]

Individuals

[cleon @cleondesigns]

another day, another SVG + @motiondotdev exploration

inspect element below 👇

[shaahid @shaah1d]

The loader I posted got 80k views, so I built a set of 6.

Link in reply
(no signup, just copy n paste)

[Mark Lou @markproduct]

Claude 4.8 + 1 prompt

and now anyone can achieve the same results.

Prompt below 👇

[SkalskiP @skalskip92]

supervision just hit 40,000 GitHub stars!

it now powers over 6.5k open-source computer vision projects, including all my demos like basketball AI

link: https://t.co/xXMRaS4ejS

[Kiki @Mayz1169]

I used AI to create this weather broadcast, and I'm pretty happy with how it turned out

All it takes is one image and a prompt

Workflow 👇

[DANN© @DannPetty]

Paper is becoming a major contender for the best vector creation tool.

Also it’s SVG generations and vectorizations are powered by Quiver’s Arrow 1.1 — let’s go!

[Aoden Teo @AodenTeoMT]

Today, we’re excited to introduce Miso One, the most emotive voice model in the world.

Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.

We’ve open-sourced the model weights, with API access coming soon.

Hear how Miso One sounds in the thread below.

[FHILY👑 @Oluwaphilemon1]

Motion design with Claude + Higgsfield MCP 🧩

Turn a single text prompt into pro-level motion videos.

It’s actually insanely simple:

1. Describe your idea to Claude
2. Ask it to generate a storyboard
3. Pick your favorite concept
4. Let Higgsfield MCP render the final video

[Eren Chen @ErenChenAI]

Would love to have this little desktop robot at my workspace 🤖

[原始人 @mafeb20260225]

スタイルも顔も完璧な爆美女に逆ナンされるとか人生勝ち組すぎんだろ…
1：45のボディータッチ半端ないって…

[Design Chief Priest @dnaijatechguy]

Adding the glitch effect to loaders is one of my favorite things to do😅.

[Mohib Arshi @arshi_mohib]

🚀 Screenforge v0.6.3 is out now

Cinematic Zoom is live 🔥

Based on the amazing feedback people shared on the feature, I went back and tried improving it further.

The demo below is a combination of Cinematic Zoom + 2D Zoom. Feels a lot more cinematic and flexible now.

🔊 Sound on.

Let me know if we cooked with this one.

Other updates in v0.6.3:
• Hide the cursor completely
• Cut camera clips, reposition the camera, and smoothly transition between shots

Download link in the comments.

[UI/UX Savior @UiSavior]

Shape design like a pro 🫡🫡

[Design Chief Priest @dnaijatechguy]

Most loaders are forgettable. I built this as a design exploration at Mistral to see what happens when they’re not.

Today, I’m open sourcing it. Build something wild, tag me, and send over any feedback or bugs you find.

[开发者Hailey @IndieDevHailey]

🔥 前端动画界的老大 GSAP，又扔出了一颗炸弹：gsap-skills！

90% 的网页动效只是乏味的淡入淡出，但 Apple 风滚动、数据可视化动画、沉浸式产品页背后的秘密，全在 GSAP。

GSAP 官方直接放出 gsap-skills：
支持 Cursor、Claude Code、Copilot、Google Antigravity、Windsurf 等几乎所有主流 Agent，自动识别。

神亮点：
- 25+ 高级动画实战案例，一键学会 Timeline、ScrollTrigger、Ease 等核心技能
- 让 AI 或开发者都能瞬间生成丝滑、专业、高级感爆棚的动效
- 免费开源，商业项目直接用
- 性能极致流畅，复���动画也不卡顿
- 跨框架支持：React、Vue、Svelte、原生 JS 全覆盖
- 官方教程 + 实战案例 = 动效学习最快捷径

GSAP 本身已全部免费（原 Club 高级插件全部白送），现在再加上这套官方 skill，装完直接甩需求给 AI，感受 Apple 级动效秒出的爽感！

[Praha @Praha37v]

Now you know whom to hire for isometric websites.