Creator of img2threejs | BuyMeACoffee: ko-fi.com/iamnick | Community: discord.gg/fX9r3cVth2 | Youtube: piped.video/@img2threejs

VietNam
Pinned Tweet
A BIG update for img2threejs. It’s been almost 2 months since I launched img2threejs. After a lot of experiments, feedback, and seeing where people struggle, I realized there are some changes we simply have to make if we want this project to go much further. So here’s what’s changing: / 01 / A new ROADMAP: from one pipeline → a plugin-able ecosystem This is the biggest change. Reconstruction, environments, rigging, animation, VFX/SFX, exporters, providers… shouldn’t be locked inside one giant workflow. The goal is to make img2threejs modular: use what you need, replace what you don’t, build your own workflow, and eventually your own plugins. I believe this is the right foundation for img2threejs to grow from an open-source project into an ecosystem. ⁠Read the new Roadmap → github.com/img2threejs/img2t… / 02 / Playground The simplest way to use img2threejs: upload an image → wait ~10 minutes → get your 3D asset. Export to different 3D formats or directly to pure Three.js code. / 03 / Studio This is for those who want full control. Watch img2threejs build in real time: Nano → Texture → Rigging → Animation → VFX/SFX → Export. Configure, inspect, and control the workflow instead of only receiving the final result. / 04 / A new Landing Page Cleaner, easier, and actually more useful. You’ll be able to copy prompts directly, explore examples, and export assets for Blender or your own workflow. I’m trying to wrap up as much of the annoying work as possible animation, rigging, textures, exporters, so you can focus on building. / 05 / Official YouTube Many of you have asked how these showcases are actually built, and X simply isn’t the right place for a 20–40 minute walkthrough haha. I’ll start sharing full step-by-step workflows, experiments, tutorials, and project updates here: ⁠YouTube → piped.video/@hoainho1465 And one more thing… Tomorrow at 13:00 UTC - img2threejs × GPT-6 Astra. A new exclusive showcase is coming. I’ve spent enough time with img2threejs that I thought it was getting difficult to surprise myself anymore, but this one did. To everyone who tested img2threejs, contributed code, reported bugs, shared feedback, created something with it, sponsored us, became a partner, or simply told me to keep going - thank you, truly. A lot of what you see in this new direction comes directly from those conversations. We’re still very early, and there’s still a ridiculous amount of work ahead, but I’m really excited about where this is going. If you’re building in AI, 3D, graphics, or creative tools and this direction makes sense to you, I’d love to connect. Maybe we can build something together haha. Community: discord.com/invite/fX9r3cVth… Support: ko-fi.com/iamnick Same vision. Bigger possibilities. — Nick
10
15
134
7,418
For anyone asking how to get started with img2interior, here's a quick video tutorial! It's super simple. Just copy the prompt, paste it into your AI coding agent, and let the skill handle the rest. Give it a try! 😄 🎥 piped.video/watch?v=m4dDK7nO…
Just released img2interior v2.2 — a new open-source plugin for the img2 ecosystem! Turn a single reference image or your imagination into a fully editable 3D interior using Three.js. It's free: github.com/img2threejs/img2i… If you find it useful, a ⭐ on GitHub would mean a lot! Anyone interested in trying it out?
1
4
38
4,011
If you find this helpful, don't forget to subscribe! ❤️ I'll be sharing more tutorials, demos, and step-by-step guides on this channel more often. Stay tuned!
1
3
80
Just released img2interior v2.2 — a new open-source plugin for the img2 ecosystem! Turn a single reference image or your imagination into a fully editable 3D interior using Three.js. It's free: github.com/img2threejs/img2i… If you find it useful, a ⭐ on GitHub would mean a lot! Anyone interested in trying it out?
10
39
378
21,203
And don't forget, I've also added export support! 😄 You can export your 3D interiors and reuse them in your own projects whenever you want. Feel free to make them your own!
314
Another step toward making 3D creation more accessible with Three.js Excited to share img2interior v2.2 with the community! ❤️
Just released img2interior v2.2 — a new open-source plugin for the img2 ecosystem! Turn a single reference image or your imagination into a fully editable 3D interior using Three.js. It's free: github.com/img2threejs/img2i… If you find it useful, a ⭐ on GitHub would mean a lot! Anyone interested in trying it out?
3
1
14
621
Try the live demo: img2threejs.io/living-room/
5
1,267
Turning static pixels into living, playable worlds My latest img2pixi2D experiment explores turning a static 2D image into a fully animated, playable platformer. The process: - Analyze characters, objects & environments - Bring the scene to life with animations - Expand beyond the original image - Add movement, physics, enemies & interactions From a single reference to an explorable world. Built with PixiJS + AI coding agents. 🌱 Open source: github.com/img2threejs/pixi2…
12
27
252
11,200
For anyone curious about the workflow: 1/ Generated a 2D platformer level image using ChatGPT. 2/ Used the img2pixi2D skill to turn it into a playable game with animations, physics, enemies, and VFX. 3/ Did some final UI polishing, testing, and bug fixes. Total time: ~20 minutes from a static image to a playable game! 🎮 I think this workflow could be really useful for quickly prototyping game ideas and building playable MVPs without spending days on development. A great way to test an idea before investing more time into it!
4
541
Exciting to see what the @OpenBMB team is building! I’m particularly interested in exploring how MiniCPM-V 4.7 can support image-to-code workflows, especially visual understanding and spatial reasoning. Looking forward to testing it with img2threejs. Congrats on the release!
🚀 PilotDeck 2.0 is here! Meet the open-source AI Agent Harness built to get complex work done. Developed by Tsinghua THUNLP, @modelbest_ai, @OpenBMB , and AI9Stars, PilotDeck is a model-agnostic Agent operating system that turns natural language instructions into completed tasks — with transparent data flows and the freedom to choose your models. What’s new in 2.0? 📄 End-to-end office work: Create, edit, and verify Word, Excel, and PowerPoint files — not just generate drafts. 🔄 More reliable execution: complex, long-running tasks going through interruptions. Stress-tested with 2,000 interaction messages. 🛠️ Easy to get started: One-click desktop installation and a streamlined setup flow to connect your model and create your workspace. 🔓 Open by design: Fully open-source, model-agnostic, with data flows visible to users. On Workbuddy Bench, PilotDeck scored 79.1 with Qwen3.6-35B-A3B, outperforming WorkBuddy (74.7) and Claude Code (77.3). Build your own AI workspace for the Agent era. 🔗 GitHub: github.com/OpenBMB/PilotDeck Web: pilotdeck.openbmb.cn
363
One image - One playable world 🎮 I turned a static pixel-art image into a mini 2D RPG using img2pixi2D. Movement, combat, NPCs, quests, and mobile controls. Built with @PixiJS and ~600K AI tokens. This is just the beginning. 🔗 github.com/img2threejs/pixi2…
2
10
782
Always exciting to see new vision-language models entering the scene! With img2threejs, I’m particularly interested in how MiniCPM-V 4.7 handles visual understanding and spatial reasoning. Looking forward to putting it through some real-world tests. Congrats to the @OpenBMB team on the release!
🎬 35B MoE multimodal AI. On your phone. With just 3GB of memory. 🤯 This is MiniCPM-V 4.7 in action: reading real-world signs, planning around constraints, parsing complex documents, and reasoning over visual data. Powered by LES (Lookahead Expert Scheduling), the 35B-A3B model brings efficient MoE inference to mobile devices, while the lightweight 1B variant delivers capable multimodal understanding on resource-constrained hardware. 🛠️ With Self-Replay Fine-Tuning (SRFT), developers can customize models for new tasks while maintaining general performance. From iOS to Android, MiniCPM-V 4.7 makes powerful multimodal AI more practical to run locally. Try it 👇 🔗 github.com/OpenBMB/MiniCPM-V 🤗 huggingface.co/collections/o… Self-Replay Fine-Tuning: openbmb.cn/en/blog/self-repl…
1
2
370
🌤️ New Plugin Release: img2pixi2D! A lot of you have been asking about 2D game development, so I decided to build something for it! With img2pixi2D, you can turn images into interactive 2D games, animated scenes, or even bring your portfolio and landing pages to life using @PixiJS . Opensource: github.com/img2threejs/pixi2… 🚀 Quick Install: 1/ npx --yes @img2threejs/pixi2d@latest install --yes 2/ Start a new OMP session and use /skill:img2pixi2d in your PixiJS project. The showcase below has just one prompt and ~280K tokens. This one started as a random idea. I built the skill pretty quickly, just for fun, and thought it was worth sharing! Sometimes the best ideas come from unexpected experiments. Give it a try and show me what you build! 🔥 #img2threejs #PixiJS #GameDev #2D
5
18
1,242
From a single image to a fully animated 3D character! Excited to team up with @tripoai and @thebuggeddev for a live workshop! We’ll explore how to generate 3D models with Tripo, turn them into editable Three.js code using img2threejs, and bring them to life with animations, VFX, and AI-powered workflows. 📅 October 12 | 14:00 UTC 📍 Live on Discord Come hang out, learn something new, and see what’s possible when AI meets 3D development! #Threejs #TripoAI #img2threejs #AI #WebGL
3
2
15
3,382
Its time to enjoy... 🤡
55
You’ve seen me build all kinds of 3D websites, and many of you have asked how to create something like that yourself 👀 So we’re making it happen I’m teaming up with @tripoai and @NickDevFE, the creator of img2threejs, for a live workshop where we’ll show you exactly how to do it. Here’s what you'll learn 👇 ✴️ Generate detailed, high-quality 3D characters with Tripo AI ✴️ Reconstruct 3D models as editable Three.js code using img2threejs ✴️ Modify geometry, customize individual components, and refine model details ✴️ Rig characters, create, repair AI generated animations, and VFX ✴️ Integrate everything into an immersive, interactive 3D website using Three.js And if you attend, there’s something FREE waiting for you, along with another surprise we think you’ll love 💛 🗓️ October 12 at 14:00 UTC 📍 Live on Tripo AI’s Discord Join us: discord.gg/84xJc7QzW And if there’s anything you’d like me to cover during the workshop, let me know below :)
3
4
39
6,248
Who says you need the biggest AI models to build 3D worlds? img2threejs turns a single image into a fully editable Three.js scene. But the tool is only half the story. The heavy lifting is done by the vision-language model behind it. That model has to: → read the image and understand layout, depth, objects and materials → turn what it sees into working Three.js code → look at its own render, spot what's off, and fix it Most people assume only frontier models can handle that. So I plugged in AntLing Flash VL 3.0 with img2environment, an upcoming plugin for img2threejs. ( This plugin will be released on Monday Oct 12 ) It held up better than I expected: 1.⁠ ⁠Picks up spatial layout and depth reliably from a single image 2.⁠ ⁠Writes clean, structured Three.js and TypeScript you can actually edit 3.⁠ ⁠Catches its own mistakes by comparing each render against the original 4.⁠ ⁠Does all of this at a fraction of frontier-model cost The trade-off: it needs a few more refinement passes to get there. But every pass is cheap, and the final scene is solid and fully yours to modify. I believe AI-powered 3D development shouldn't depend on how much you can afford to spend on tokens. If you're curious, plug AntLing Flash VL 3.0 into img2threejs and see what it builds. Here's what I got 👇
4
4
29
10,104
Here's a reference image I used for this showcase:
1
175
This was ONE image. Now you can walk into it. ❄️ Not just the cabin. Not just the character. The whole scene. Hyper3D × img2threejs × Three.js × GPT-6 Luna The workflow starts with a picture of a world. img2threejs analyzes what’s inside: the house, trees, rocks, character, and their arrangement. Hyper3D provides the 3D references. GPT-6 works through the img2threejs pipeline to reconstruct the objects and bring them together in Three.js, rebuilding the scene with depth, lighting, and interactions. But recreating the picture is only the beginning. Walk around the cabin and leave footprints in the snow. Open the gate. Turn day into night. Place a campfire and watch the world take on a different atmosphere. You’re no longer limited to the moment or camera angle captured in the original image. This isn’t just making a picture move. It’s rebuilding what’s inside it into a world you can explore, edit, and keep building. One image sets the scene. You decide what happens next. Opensource: github.com/img2threejs/img2t… @DeemosTech @threejs @OpenAIDevs #img2threejs #opensource #imageto3D
10
16
135
10,996
Here's an image reference I used:
Made with AI
2
117