Ciao

家有柴，早起遛，迷迷糊

[Ding @dingyi]

想学 Heygen 和 Hyperframes 一定要 fork 官方的这套视频案例。https://t.co/drpwry2iRA

[Qiusheng Wu @giswqs]

GeoLibre v2.3.0 is here!

GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private.

This release brings a legend that writes itself from your symbology, a new GeoLens catalog browser, and 200+ GeoLibre Rust geoprocessing tools running entirely in the browser.

What's new in v2.3.0

- Automatic on-map Legend: the legend builds itself from your visible layers, with class rows for graduated, categorized, rule-based, and expression styling, gradient bars for heatmaps and raster colormaps, and land-cover labels from a Raster Attribute Table. Rename, hide, reorder, or add your own entries, and it saves with the project.
- Symbology swatches in the Layers panel: every row shows a dot, line, square, or image glyph in the layer's own color, so a tall layer stack reads at a glance.
- GeoLens catalog browser: connect to a self-hosted GeoLens server, search its catalog, and add datasets as vector tiles, GeoJSON, or rendered raster tiles.
- Emerging Hot Spot Analysis: build a space-time cube from timestamped points and classify every cell as a new, intensifying, persistent, diminishing, sporadic, oscillating, or historical hot or cold spot, all client side.
- Mosaic time series: the Time Slider now steps through MosaicJSON and STAC collections of many COGs per date, on either a GPU or a WASM rendering engine.
- Copy and paste layer styles: give a whole set of layers one consistent look without restyling each in turn.
- Shareable tool links: deep-link any Whitebox tool with a ?tool= URL that opens the dialog preselected and pre-fills the form, with a Copy link button to build it for you.
- Smarter data loading: pick which layers to load from a multi-layer GeoPackage, import CSVs whose coordinates are in any projected CRS, and read a raster's real CRS, pixel size, and extent from the metadata dialog.
- Multiple AI profiles: define several provider, model, and credential setups, pick a default, and switch between them from the assistant panel.

Try it out

- Launch GeoLibre Web: https://t.co/8gMtkVtfnm
- GitHub: https://t.co/VXq8c1o2Nd
- Documentation: https://t.co/7VA2AQoCUc
- Release notes: https://t.co/cf3fXneeh6

#GIS #Geospatial #OpenSource #RemoteSensing #MapLibre #GeoLibre

[Meng To @MengTo]

I'm open-sourcing my Three.js game dev skills.

Build an isometric action RPG with camera controls, VFX, audio, monster assets, combat systems, and more.

Everything is free:
https://t.co/BoiGY8zvA9

Play the game:
https://t.co/ylWrybZMns

Game assets:
https://t.co/FlOc22IT5v

[Yasir Ai @AiwithYasir]

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time.

one camera. no LiDAR. 10,000+ frames without falling apart.

just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps.

→ runs at ~20 FPS on a single GPU
→ Stable over 10,000+ frames
→ Beats optimization-based methods on benchmarks
→ Works on drone footage, driving videos, indoor walkthroughs

100% open source.

[Blurr @blurrhaus]

One click. Fresh variations.

https://t.co/cA3W8afT6m

[Beginnersblog @beginnersblog1]

Workflow:

Made this cinematic football short with a surprisingly simple workflow:

- Created the character sheet in ChatGPT
- Generated 3 connected storyboards (10 frames each)
- Converted each storyboard into a detailed Seedance 2.0 video prompt
- Generated all scenes in Seedance
- Edited everything together into one film

Character → Storyboards → Video Prompts → Seedance → Final Film.

[Gabriel @gabriell_lab]

Since Opus 4.8 is out and more and more designers are getting into Design Engineering, I thought I’d share some of the interaction patterns I use most often:

Use proximity, not just hover. When the cursor gets close, nearby elements can subtly scale and darken based on distance.

It makes interfaces feel more responsive, less binary, and way more alive

onpointermove = e =>
document.querySelectorAll(".dock>*").forEach(el => {
const r = el.getBoundingClientRect();
const t = Math.max(0, 1 - Math.abs(e.clientX - r.x - r.width/2) / 120);
el. style.scale = 1 + t * .5;
});

[Beginnersblog @beginnersblog1]

This is one of my best AI-short films I've created in 10 hours.

Still need to put a lot of work to finish this project.

[Kiki @Mayz1169]

This kind of Eastern action aesthetic goes so hard 😭

made with GPT Image 2 + Seedance 2

Prompt⬇️

[el.cine @EHuanglu]

AI is ready to make full films

Seedance 2.0 now can read your entire shot list to generate a full story.. keep characters, props and set design consistent with one image on BytePlus

duration and consistency is not a problem anymore

here's how with prompts:

[INK @0xInk_]

To finish first, first you must finish.

made with Midjourney v8.1 and Seedance2

[Larus Canus @MrLarus]

🤯太震撼了！
我用ChatGPT-Image2全新生成《3D历史人物立像档案》，气场爆炸！🔥

把一个人的一生，浓缩成一座可以阅读的历史立像：
诸葛亮、王阳明、张居正、曾国藩
中央是全身3D人物，手中的书卷破框而出
一生高光画面散落在时光碎片里，人物立体气场逼人！

提示词参考评论区👇

[Abdul Șhakoor @abxxai]

What AI is doing right now is insane.🤯

ChatGPT Image 2 turns your ideas into full storyboards with cast and scenes… then Seedance 2 turns those into full cinematic shots.

Exact prompts below 👇

[Beginnersblog @beginnersblog1]

GPT Image 2 + Seedance 2 = cartoon chase scene.

I wanted to see how far I could push storyboard-to-video consistency, so I created a full 15-second cat vs mouse sequence inside a completely destroyed house.

The process was actually simple:
- generated a 3x3 cinematic storyboard sheet in GPT Image 2
- designed every frame like a real animation pre-production sketch
- added camera directions, motion cues, timing notes, and destruction progression
- used Seedance 2 to animate the entire sequence into one continuous cinematic shot flow

What surprised me most was how well Seedance 2.0 understood the visual continuity between frames. The flying debris, motion blur, exaggerated jumps, and camera movement felt surprisingly cohesive.
.
.
.

[Okan Can @0kncn]

GPT Image 2 ile storyboard çizdim,
sonra Seedance 2.0 ile bunu tam animasyon sahnesine çevirdim
Bir rakun.
Bir donut.
Ve tamamen kontrolden çıkan çizgi film kaosu.

Storyboard → cinematic cartoon video dönüşümü gerçekten deli hissettiriyor.
AI artık sadece görsel üretmiyor, timing ve slapstick komedi de kurabiliyor
Ve en absürt kısmı:
Bunun tamamını sadece 10 dakikada yaptım.

[Kōda @aimikoda]

GPT Image 2 + Seedance 2.0 Prompt Share

Tried using IPA + FACS for a contemporary performance piece where live singing and choreography happen simultaneously. Not sure how much of it actually worked technically but I think the final result turned out pretty interesting.

I also ended up color-coding the storyboard annotations because otherwise annotations were confusing the model. Different colors helped separate body movement, camera motion, framing and lighting directions from the actual environment and character drawings.

You can find color-coded storyboard prompt + seedance 2.0 prompt in the replies.

[Dilum Sanjaya @DilumSanjaya]

Fun interactive science app ideas | Part 3

Played around with generating 3D biological structures and made an app to explore them interactively

UI Design
GPT Images 2

Code
Gemini 3.1 Pro

More demos ↓

[古一 @MANISH1027512]

现在我生图基本都交给 Codex 了，尤其是各种自动化任务。

昨天一天，它给我跑了 300 多张图。

但有个问题：这些图默认都会存在 Codex 的本地生成目录里，而我平时管理图片、视频、参考素材，主要都在 Eagle 里。

正好 Eagle 提供了 MCP，可以让 Agent 操作 Eagle App 里的大部分能力。

所以我干脆写了一个 Skill：codex-image-to-eagle

它主要有两种用法：

1.手动调用
比如直接对 Agent 说：
“帮我把今天所有 Codex 生成的图归档到 Eagle。”

2.自动调用
在自动化生图任务里加一个 hook：每生成一张图，就自动归档到 Eagle。

归档时会自动按日期分类，更重要的是：
每张图对应的 prompt 也会一起写进 Eagle 注释里。

这样之后翻图、复盘、找提示词、做二次创作，就不用再到处翻文件夹了。

我已经把这个 Skill 开源了：
https://t.co/oSesN13cNb

你可以直接让自己的 Agent 安装，基本开箱即用。

前提是：你得有 Eagle，并且开启 Eagle MCP。

如果你还不知道 Eagle 是什么，建议你了解一下。

这几乎是我们社群里玩 AIGC 的人手一个的本地图片 / 视频资源管理神器。

[Kashberg @Kashberg_0]

GPT IMAGE 2 & Seedance 2.0

That’s so awesome 🔥

[KANA｜東京AI映像 @KanaWorks_AI]

ChatGPT-Image-2.0 × Seedance 2.0｜ゲームUI切り替え🐰
まさかAIでここまでのUI切り替えができるとは思わなかった。ChatGPT-Image-2.0でのUIデザインはすでにかなり精度が高い。
Seedance 2.0で動画化する段階ではまだ課題あり。「操作レベル」での精密なコントロールは依然として難しい。
AEやUnityなら一度フローを構築すれば安定して再現できるが、AIはまだ「生成ベース」で、言語だけで結果を完全に固定するのは難しい。
それでも効率は確実に上がっている。
以前はUI一式を組むのに最低でも1週間。
今回は初回でも約3時間で一通り完成。
100%の一致を求めなければ、その後の再現はかなり速い。
PPTやプロダクトデモ用途なら、すでに十分実用レベル。
ゲーム業界、変わり始めている🤯

GPT Image 2.0 × Seedance 2.0 on @higgsfield