THIS IS F**KING GOLD
475 VIDEO DEMOS BUILT WITH CLAUDE OPUS 5.5 IN ONE GITHUB REPO
Motion graphics, explainers, 3D scenes, and even games, all made with HTML, Canvas, SVG, and Three.js.
The crazy part? Every demo comes with its original prompt and source post, so you can pick any one and try recreating it yourself.
475 examples to learn from and experiment with.
Repo in the comments 👇🏻
You don't need a multi-camera studio setup, expensive suits, or cloud subscription software to do performance motion capture anymore.
A single video file inside Blender is all it takes.
Arcomade just released BlendCap—a 100% local, offline Blender add-on that extracts full-body, hand, and facial tracking directly from video footage.
It maps performance straight onto Rigify, Auto-Rig Pro, Mixamo, or CloudRig setups and includes instant FK-to-IK conversion for fast keyframe cleanup.
For solo animators and indie game devs: would you use video mocap for primary animation, or just for blocking out initial poses? #b3d #mocap #indiegamedev
🚨 UPDATE: MASS MIGRATION EXPLORER 🚨
NOW WITH THE OVERSIGHT PROJECT 🤝
🔎 FOLLOW THE PEOPLE. TRACE THE MONEY. 💰
Last time I promised the FEMA pull. It's done, and I went further.
The Mass Migration Explorer is now a joint project with @ItsYourGov. Together we've added the money that paid to shelter migrants after they crossed, and it reaches past the federal government into city and state budgets.
What's new:
✅ FEMA shelter money: every Shelter and Services Program award, followed to the NGOs that received it.
✅ City and state contracts: New York City, Chicago, Denver, San Diego, Pima County, El Paso County, California, Massachusetts and more. Money for migrant shelters ran through local governments too.
✅ A "Migrant shelter money" filter that pulls the whole shelter pipeline onto one screen.
✅ 1,275 organizations, every link backed by a USAspending award, an IRS filing, a FEMA allocation or a city contract record.
✅ See what was cut: 150 awards ($537M) terminated, cut short or clawed back since Jan 20, 2025. That includes the FEMA shelter funds pulled back on Feb 10, 2025.
Everything from the first release is still there: the border chart (monthly encounters down 96%), the county map back to 1990, the 116 explained county jumps, the legal-pathway layers and the faith-network filters.
💡 This money stopped because voters changed who was in charge. Keeping it stopped takes more Republicans in Congress. Vote straight Republican Nov 3. 🇺🇸
👇 Try it now: [link in next post]
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.
Nano Banana 2.1 holds one face steady through a full run of micro-expressions, all in a single image.
Seedance 2.5 takes that image as reference and plays the run out in order.
Both models, one API.
⬇️ Prompt:
Reference image: use the same man, LEON, from the reference image. Keep his face shape, pointed chin and V-shaped jawline, facial proportions, dark grey-brown hair, black turtleneck and charcoal coat collar exactly the same. Real skin pore texture, cinematic lighting. His fringe falls just above the brows, and both brows stay clearly visible in all five frames.
Layout: ultra-wide 4:1 banner, split left to right into five equal close-ups (head to collarbone), each panel framed vertically. Between panels, a full black divider about 12px wide running top to bottom. White circled numbers ①②③④⑤ in the top-left of each panel. Thin white arrows → above the dividers between the first four panels, no arrow after ⑤. No text anywhere except the numbers and arrows. Same camera, light and cool dark grey background across all five panels.
Theme: a helpless, cold smile, tears welling in his eyes. He blinks them back, and in the end lets out a resigned laugh. Not a single tear falls the whole way through.
① Helpless cold smile:
Only the right corner of the mouth tugs up slightly, the left stays still, an asymmetric smirk.
A soft breath out through the nose.
Eyelids slightly lowered, gaze a little downward.
A very faint lift at the inner brows, a hint of tiredness and resignation.
② Tears welling:
The smirk is still on his mouth, but it has frozen.
Lower lids brimming with tears that swim in his eyes, catching the light, not falling.
Inner brows clearly raised, gaze turned up and away from the lens.
Jaw slightly tightened.
③ Blinking the tears back:
Catch the instant he blinks: both eyes squeezed shut, lashes wet and clumped together.
Brows slightly knitted, lips pressed together, jaw held tight.
The tears still don't reach his face.
④ Eyes open, tears held back:
He opens his eyes again, chin lifted a little, looking slightly up, using that angle to keep the tears from falling.
The whites of his eyes wet and glossy, rims damp, but his cheeks dry with no tear tracks.
Nostrils flared slightly, like he's drawing a deep breath.
Lips pressed into a line.
⑤ A resigned laugh:
Gaze drops back to the front, head lowered slightly.
Both mouth corners lift briefly, showing a little of the upper teeth, like a bitter laugh through the nose.
A few real smile lines at the corners of the eyes, but the inner brows are still raised, the sadness hasn't left.
Eyes moist, no tears falling, cheeks clean.
Skin tone lock: all five panels keep the natural skin tone of the reference image. No redness on the cheeks, nose tip or forehead; only the very edge of the eye rims may show a faint wet redness.
Style: realistic film still, 85mm lens, shallow depth of field, soft side light, real skin texture and light reflecting in the tears, high detail. No cartoon look, no smoothed plastic skin.
@atlas_cloud_ai How do I get the First Top-up Special: Get 20% bonus back on your first deposit? I bought $25 already but will buy some more if I can get this credit. Please DM me thanks!
After six years in stealth, Atomic Machines is out. Our mission: on-demand, universal command of matter. First beachhead: the Matter Compiler, an AI-native manufacturing system that builds working micro-machines from code alone. No per-product tooling. No process development. Different code, different machine.
AI is now being used to recreate Adobe’s software, a developer has released seven free, open-source apps as clean-room alternatives to Adobe’s main tools:
- PhotoCraft → Photoshop
- VectorCraft → Illustrator
- FilmCraft → Premiere Pro
- LightCraft → Lightroom
- EffectCraft → After Effects
- DesignCraft → InDesign
- PrintCraft → Acrobat Pro
Built in Rust with help from Claude Opus 5.5, they run on Windows, Linux, and macOS under MIT/Apache licenses without using Adobe’s source code.
This is the doom I predicted a few days ago, coming for Photoshop. A clean-room open-source reimplementation.
No prizes for guessing that they decompiled Photoshop to source code, processed that to some kind of non-code specification language, then fed the spec to an LLM with an instruction to generate Rust.
Adobe just got nuked. And closed source is dead, dead, dead.
https://t.co/0sxtGNaPtq