Santa Monica, CA
Joined May 2007
🚨 Site relaunch! dulce.com 🚨 Interactive 3D scenes (Babylon.js) , 4 animated AI avatars (Three.js + Blender), A 3D/VR web shop is coming soon for mesh & digital products, built for Meta Horizons & WebXR Now booking new clients for immersive web & avatar projects.
2
352
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
5
13
345
18,928
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
got to check out this sick demo by @semateos and attend @tripoai Tripothon with @mielke_jack
1
3
10
361
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
I legitimately forgot how much I adore this movie. He's animated on ONES to match the live action footage. That's 24 drawings per second for 1 hr 44 min 6,240 Richard Williams was deranged and I highly recommend his textbook/video series for those learning animation basics.
32
1,379
12
15,313
343,845
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
Viewport vs Render, Blender 4.2 Eevee
Viewport vs Render, Blender 4.2 Eevee
3
27
605
17,173
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
🚨 Claude Fable 5.1 vs GPT-6 Astra (today) Same exact prompt ↓ But Astra's output looks noticeably weaker less detail, less polish, and the overall result just doesn’t hit the same It honestly feels like Astra got little nerfed
71
54
24
883
89,542
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
おはようございます☀ 以前はモーションキャプチャを録画して3Dオブジェクトに適用させてたけど、面倒になったので直接Blenderで動かせる様にしたよ!!
15
91
4
1,074
57,109
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
THIS IS GENUINELY THE MOST TERRIFYING THING I'VE EVER WATCHED they took the full wiring of a fruit fly, 166,700 neurons, and plugged it into an android hanging from the ceiling the fly it came from has been dead for years 1,000 artificial muscles, a skeleton, no face the fly brain was built for six legs and two wings this body has two legs, two arms and nothing to fly with nobody told it > minute 1, a twitch in the fingers > minute 4, the toes start curling like it's testing what it's attached to > minute 9, the knees lift one after the other, it's trying to walk on air > minute 20, someone walks underneath it and the kicking speeds up, you can hear the cables creak > minute 31, the lights go off and every muscle locks at once it found the rhythm a fly walks with and forced it onto human legs and when the lights went off, it did exactly what a fly does when a shadow passes over it, it froze and got ready to launch then came the part that made the room go quiet > it brought both hands up to its chest > started rubbing them together > slowly, over and over > the way a fly cleans itself there is no code in that body that tells it to do that it's 166,700 neurons doing what they've done for millions of years, inside a body they were never meant to have right now the cables are the only thing holding it up it learned to walk in one afternoon nobody wants to find out what it learns in a month and the next brain they're mapping is a mouse, 70 million neurons, about 400 times bigger than this one
Readers added context they thought people might want to know
This footage is Clone Robotics' Protoclone, which went viral in Feb 2025 twitching while suspended—before the fly connectome (MaleCNS) was released in Sept 2026. Protoclone has never been shown standing or walking unaided; it's suspended because it can't yet support itself. blog.robozaps.com/b/clone-protoc… livescience.com/technology/rob… ibm.com/think/news/fru…
304
714
211
5,500
1,271,680
My childhood drawing and my kid's drawing, alive and playing together in VR 🖍️✨ Dear Little Me turns kids' drawings into 3D friends with @TripoAI, then you step into worlds made from drawings. youtu.be/zKGediVXzBI Try it: dear-little-me.vercel.app #Tripothon
1
2
136
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
“People are worried the studio doesn’t need the artist. It’s the artist that doesn’t need the studio.” mic drop. 🦾
Denzel explica por qué usa la IA. Un pequeña prueba explorando Minimax H3 en ComfyUI con mis nodos y métodos de inpainting.
111
157
24
2,165
214,779
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
I just recreated the legendary Canelo vs. GGG fight in Blender using GPT-6 Astra, move for move. feels fun ngl
163
536
43
5,756
874,631
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
Iridescent Study 🔊
33
161
9
918
23,113
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
18
67
7
1,057
54,670
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
26
136
19
2,895
95,055
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
51
193
22
4,027
162,371
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
Check out this 👀 Super useful Blender Free add-on for automatic hand rig grabbing. Love seeing workflow tools like this from the community. @xan2622 links in comments 👇 #B3D #Blender3D #Animation
3
71
1
801
27,392
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
A quick @threejs experiment exploring an infinite carousel of liquid glass tiles, rendered in real time with WebGPU and TSL. Each card is a thick refractive slab sitting on a curved grid that never ends. Short explanation of how the glass is rendered in the thread 👇
32
65
16
992
58,838
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
[👁️👁️]
43
544
26
6,813
163,981
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
We just tested what might be the most accurate motion transfer workflow we've seen so far. It's a little more involved than a standard workflow, but the results are pretty impressive. Here's the basic workflow: 1. Start with your reference footage. Create character and environment references. 2. Convert the reference footage into a depth map (with Depth-Anything tool on Fal: fal.ai/models/fal-ai/depth-a…). 3. (Optional) Layer on additional guidance like colorized character masks (with Meta's Segment Anything: huggingface.co/spaces/FudanC…), and or skeleton poses (with Framethrower.ai). 4. Feed the depth map into Seedance 2.0 Omni as your motion reference along with your character and environment references. 5. Generate your final video. After testing several variations, the depth map workflow consistently produced the cleanest and most accurate motion transfer. If you're trying to recreate specific performances or complex movement, this is one of the closest AI workflows we've seen to achieving production-quality results.
12
62
3
542
31,478
Dulce Dotcom | Mixed Reality Artist | dulce303.eth retweeted
【精度高いAIダンス動画の作り方】 ダンスモーションを深度マップに変換してSeedance2.0でキャラとモーション動画を参照させてダンス動画作ってみた! 引用元1p ( @impalementd )さんの作り方を参考にさせていただきました! 深度マップにするとモデルに渡す情報が「動き」だけになるからなのか、ダンスの精度が高くなってる気がします。 そして、KnRoco ( @roco_kn_roco )さん、おじさんダンスのアイデアありがとうございました☺️
원하는 댄스 커버 무한으로 찍어내는 방법 커버 영상 만들 때 저작권 이슈 터질 때 있지? 이걸로 간단 해결! 준비물 1. 마음에 든 15초 이내 동영상 저장 2. 영상의 Depth를 추출하는 사이트를 클로드로 제작 3. 만들어진 사이트에 영상을 넣고 Depth 영상을 추출 4. 하단 프롬프트처럼 넣고 제작!
31
323
29
2,527
465,803