@Colado_ds

Founder MidoAI | Mentor & Strategist || E‑commerce & Automation | AI Media | Blockchain

midoai.edu.vn/
Joined October 2013
  • Tweets1.2K
  • Following801
  • Followers449
85Media
If you're making 3D art or games, bookmark this. - blender.org Make anything in 3D - polyhaven.com Free 3D models, textures, and lighting - ambientcg.com Free realistic surfaces for 3D - quaternius.com Free 3D characters and props - mixamo.com Give any character animations in one click - threejs.org Put 3D scenes inside a website - babylonjs.com Build 3D games in your browser - godotengine.org Free game engine, keep every dollar What did I miss?
27
211
11
1,758
56,797
Gordon retweeted
Ammaar Reshi
@ammaar13h
I used Gemini 4 Argon to make Subway Surfers for the new flying Tesla Roadster 🚀 Fly over moving traffic, hit the thrusters to barrel roll in the sky, and collect air power-ups to set a high score. Play + code below!
211
203
77
2,995
150,468
Gordon retweeted
Lemomo
@lemomo_aiOct 16
Lemo-Opuscar又更新了8个风格 🎇，我开了一个新的风格分支叫做【实证影响】。主要是为了有视频图片等素材的解说和知识介绍场景用的，非常实用哦。 同时，巧妙地避开了一些市面上常见的风格，希望尽可能给大家更多灵感啦！可以去更新插件啦～
Lemomo
@lemomo_aiSep 26

开源了39种风格视频库后，我学会了如何用Opus5.5稳定出片

Article · @lemomo_ai
15
31
1
185
15,183
Gordon retweeted
jtydhr88
@jtydhr8819h
ComfyArt: a fully local, open-source “Lovart” Yep, the title is exactly what it sounds like. I took Lovart as my benchmark and built a fully local, open-source alternative on top of ComfyUI. The tech stack, the UI, the features, even the name were all “borrowed.” As for what ComfyArt is and how to use it, here’s the AI summary: A free, open-source AI design canvas that runs entirely on your own ComfyUI. It has an infinite canvas (tldraw + React), a design agent that uses tools to work directly on the canvas, and every image and video model runs locally. No account, no credits, no cloud. ComfyArt is an AI design canvas that runs entirely on your own ComfyUI. It gives you an infinite canvas for posters, social media graphics, slide decks, and short videos, plus a design agent that works directly on the canvas, with all image and video models running on your own GPU. Repo: github.com/jtydhr88/ComfyArt Docs: comfyart.org/en Grab it if you need it, and have fun.
4
18
2
131
6,020
Gordon retweeted
Tezumie@TezumiesOct 14
Image-to-Pixel 3.0 is out 🎨 Turn images and video into pixel art right in your browser. Free, MIT open source. Try it: tezumie.github.io/Image-to-P… Or use it in code: npm i image-to-pixel
43
361
33
3,578
160,947
Opus 5.5にThree.jsを書かせた、3D空間で文字が動くモーションのテスト。 「切れてないよ」 ※寝る前には見ないでくださいね。 ■素材 ・物語と文字の動き：Opus 5.5 ・3Dモデル（自販機・店・電話機・人物）：Tripo ・声：Gemini TTS ・動画生成AI：使っていません ■やらせたこと ・物語を書く ・夜の電話ボックスを3Dで組み、文字の置き方と動きをThree.jsで作る ・声を合わせて、1本の動画に書き出す ■わかったこと ・字そのものを3D空間に置いて、カメラで撮れる ・場面がまるごと手元にあるので、引きも寄りも撮り直し放題。ガチャを回さなくていい ・字に演技をさせる感覚 もっと3Dのクオリティを上げると、より没入感が出そうだなと感じました。精進します。 ぜひ音ありで見てください。
11
45
7
484
27,237
Gordon retweeted
Tesla
@TeslaOct 16
Real life, baby
18,360
93,086
43,940
748,866
88,471,468
Gordon retweeted
Yi Shen
@pissang1Oct 14
My WebGPU path tracer is open source! 🎉 Physically based rendering, running right in your browser. MIT licensed. - WebGPU compute shader path tracing, with WebGL 2 fallback - Two-level BVH built using parallel Web Workers, based on TinyBVH. A 4.6M-triangle scene's BVH builds in just 0.5s on my M4 Max - Clean results from just a few samples with OIDN denoising - OpenPBR 1.1 materials - Physical camera with f-stop depth of field, AgX tone mapping, and bloom - Drop-in Three.js scene synchronization github.com/pissang/mutracer
35
61
9
554
28,003
Gordon retweeted
Leon Lin
@LexnLinOct 14
You can really build anything now Clawd animation made with Opus 5.5 Ultracode. improved sfx!
139
134
30
2,741
167,906
兄弟们，看完海外大神这个实测，我敢说： 这次在真正的“原生多模态”上，Gemini 彻底杀回王座了！ 他的原话极其震撼： “Gemini 4 Argon 是第一个让我同时感觉它 ‘既是图像、又是视频、又是语言模型’ 的存在。” 最炸裂的不是他的吹捧，而是甩出来的证据链： 他整条推特里展示的 534 幅审美极其克制、质感拉满的艺术画作—— 全部是用纯代码写出来的（Everything is made with code）！ 大厂写了这么多年代码，老哥必须跟兄弟们拆穿这背后的底层代差： 1️⃣ 以前的多模态： 缝合怪拼积木 以前所谓的“多模态”，基本是把语言模型、文生图模型、视频模型强行串联。 抽卡全凭玄学，控图全靠运气，想用代码微调一下画面，稍微改动一行就彻底崩溃。 2️⃣ 现在的 Argon： 同一个大脑在调度三界 它不是在瞎猜像素，而是把色彩空间、几何透视、构图美学全部理解透了，再精准翻译成底层渲染代码。 语言、代码、视觉，在同一个神经元网络里同时震荡。 3️⃣ 534 幅源码全开源，官方高管亲自站台 Logan Kilpatrick 亲自在下面点赞互动。 敢把整整 534 套作品的背后代码全盘公开，说明这根本不是偶尔碰运气的“樱桃采摘（Cherry-pick）”，而是工业级的稳定交付。 别再把多模态当成“能看懂截图回答两句”的聊天玩具了。 当一个模型能把绝对理性的严谨代码和极度感性的视觉审美无缝焊在一起时，传统文生图的饭碗真的要被掀翻了。 534 套源码直通车老哥放一楼了。 兄弟们觉得这种“纯代码渲染”的原生多模态，会不会是未来设计的终局？评论区开麦聊聊👇
4
1
13
2,803
a simple trick to get way better 3D results from Gemini 4 Argon while testing it on a BMW M5, the model created its own 1:1 SVG blueprints for every angle without me even asking 1st - generates flat SVG blueprints (side, top, front, rear, interior) 2nd - drops them into the 3D scene as a reference cage 3rd - checks every angle so nothing looks out of proportion this works for anything related to 3D (cars, buildings, products, Three.js, Blender, etc...) try adding this to your 3D prompts: generate 1:1 SVG blueprints for every angle first and use them as a blueprint rig to verify the 3D model
6
3
1
71
3,257
Gordon retweeted
beamnxw ./
@beamnxwOct 13
Opus 5.5 just f*cking killed the jobs of motion designers... Claude Code + Remotion = your own motion design studio give it a brief, your assets, and a reference build the scenes as editable React code 01 direct the scene layout, typography, colors, and reusable components 02 make it move timing, easing, keyframes, transitions, and layered animation 03 polish the result preview the frames, fix the spacing, adjust the pacing, and render the MP4 the clever part: your video lives in code change the headline, fonts, format, or motion curve → render again the repo: ▸ github.com/remotion-dev/remo… start a project: npx create-video@latest add the official Remotion skills: npx skills add remotion-dev/skills skills for coding agents: ▸ remotion.dev/docs/ai/skills the loop: brief → storyboard → assets → layout → animate → preview → refine → render save this, then read the full guide for Opus 5.5 Motion Engineering ↓
beamnxw ./
@beamnxwOct 9
Opus 5.5 can run a whole motion design studio Sell a 20-second launch clip built from real product screens Copy the motion engineering prompts and delivery process Build your offer before the next product launch ↓

Motion Engineering with Opus 5.5: Build Launch Videos You Can Sell

Article · @beamnxw
37
80
565
30,220
asked Gemini 4 Argon to recreate this entire video in SVG i didn't asked for photorealistic, just clean vector frames matching the original first attempt, ~20 mins on Argon high in Antigravity CLI, no follow ups it actually did it comparison with original on the side
Sundar Pichai
@sundarpichaiOct 13
Gemini 4 Argon is here. It’s available globally today for developers and enterprises in the paid tier of the Gemini API and the Gemini platform, for Ultra subscribers in Google Antigravity, and Ultra and Pro subscribers in the Gemini app and Search. Hope you all enjoy it!
24
9
4
202
14,407
We just open-sourced an entire 3D team for Blender. Introducing the Scenario plugin. Use it inside Blender, or let Claude Code run it through MCP. 📁/scenario-plugin ┃ ┣ 📁 Concept Artist ┃ ┣ 📁 Concept Art From a Prompt ┃ ┗ 📁 References From Your Viewport ┃ ┣ 📁 3D Artist ┃ ┣ 📁 Meshes From Text or a Photo ┃ ┗ 📁 Retexture or Remesh the Selected Mesh ┃ ┣ 📁 Animator ┃ ┣ 📁 Rig the Selected Character ┃ ┗ 📁 Motion From Text ┃ ┣ 📁 Surfacing Artist ┃ ┣ 📁 PBR Materials Onto Any Slot ┃ ┗ 📁 Maps From a Photo ┃ ┣ 📁 Layout Artist ┃ ┣ 📁 Greybox From a Description ┃ ┗ 📁 360 Worlds and Skies ┃ ┣ 📁 Camera Operator ┃ ┣ 📁 Camera Path From a Sentence ┃ ┗ 📁 Orbits, Dollies, Cranes and Flyovers ┃ ┣ 📁 Render Artist ┃ ┣ 📁 Viewport to Finished Still ┃ ┗ 📁 Playblast to Finished Shot ┃ ┗ 📁 Sound Designer ┣ 📁 Music, Voice and SFX ┗ 📁 Dropped on Your Sequencer Comment "BLENDER" and I'll send you the GitHub repo.
1,137
340
27
3,737
193,843
Gordon retweeted
seeco
@seeconvmOct 13
Adobe is not gonna like what Opus 5.5 can do now I’d be nervous too… Drop the PDF below into Opus 5.5, you’ll thank me later. Then save the article, it’s the only Opus 5.5 motion design playbook you’ll need.
seeco
@seeconvmOct 2

Opus 5.5 Motion Design: What the Viral 'One-Prompt' Videos Are Hiding

Article · @seeconvm
5
13
160
13,679
2/5 Step-by-step process - this was my first ever serious 3D project, but Argon made it super smooth thanks to great orchestration, multimodality and spacial reasoning.
2
3
1
98
6,452
Gordon retweeted
Motion
@motion_soOct 13
Apple just launched HomeView. So we made it a launch video in Motion. This video was one shotted 👇
Aaron
@aaronp613Oct 13
Here is the Apple HomeView launch video
1
1
13
1,884
If you're making AI videos and voiceovers, bookmark this. - github.com/debpalash/VoiceSt… Open source ElevenLabs alternative, clones any voice offline - github.com/resemble-ai/chatt… Open source voice that sounds human - github.com/Wan-Video/Wan2.1 Open source AI video, runs on your own PC - github.com/Lightricks/LTX-Vi… Open source AI video that makes clips in seconds - github.com/openai/whisper Open source captions in any language - github.com/WyattBlue/auto-ed… Cuts the silent parts out of your videos - kdenlive.org Open source video editor, no watermark - mixkit.co Free video clips, music, and sound effects What did I miss?
20
151
6
906
49,237
Gordon retweeted
Tanjim
@Tanjim38Oct 12
Few days ago We open source task management webapp. So far number doing good 390 starts. We are now improving this, Comment what you want to see! Demo: gr8r-taskmanagement.vercel.a… Github: github.com/gr8rstudio/gr8r-s…
21
47
1
703
54,906
Gordon retweeted
marcus
@marcusyulOct 12
this is exciting how ai is now getting into film and production founder's time is very precious and he/she should spend it wisely in tho things that can add revenue. and in this journey when you give 5 take for a 20 sec reels you're loosing not just time but money as well @trydrama_io will be a helping hand ig for them.. this seems something exciting happening in ai filming industry.
🤝 Paid partnership
Subhabrata Debnath
@IamFranticGuyOct 7
Introducing our new AI model @trydrama_io to kill reshoots and make acting editable! Control what part of a performance to preserve and what part to change using a simple intensity slider. We just nailed 3 industries(thread):
17
22
122
40,945
Load more