La propia nubesita

[Bilawal Sidhu @bilawalsidhu]

This new AI paper on 2D to 3D by @JingxiangSun42 et al looks promising!

“DreamCraft3D leverages a 2D image generated from the text prompt and uses it to guide the stages of geometry sculpting and texture boosting. When sculpting the geometry, the view- conditioned diffusion model provides crucial 3D guidance to ensure geometric consistency. We then delicately improve the texture quality by conducting a cyclic optimization. We augment the multi-view renderings and use them to finetune a diffusion model, DreamBooth, to offer multi-view consistent gradients to optimize the scene. We term the loss that distills from an evolving diffusion prior as bootstrapped distillation sampling.”

Code releasing soon. Project page here: https://t.co/PglSNDA55S

[Javi Lopez ⛩️ @javilopen]

Left = Original video
Right = Generated with AI

Generative AI still struggles with simulating complex facial expressions, but we are getting closer bit by bit.

💡 AnimateDiff + ControlNet x 3

[camenduru @camenduru]

DiffSketcher ✏ Text to Vector Sketch 🤯 Thanks to Ximing Xing ❤ Chuang Wang ❤ Haitao Zhou ❤ Jing Zhang ❤ Qian Yu ❤ Dong Xu ❤

🌐page: https://t.co/t7fEtz06Kc
📄paper: https://t.co/DQu4ez9slD
🧬code: https://t.co/j1a3p4DuZN
🦒colab: please try it 🐣 https://t.co/GE3BrJbiAm

[CROWLEY ESCOBAR @blackjorge]

Existe 3 tipos de magia:
1.Magia en la que el mago es el instrumento del poder divino (magia sagrada).
2.Magia donde el mago mismo es la fuente de la operación mágica (magia personal)
3. Magia en la que el mago es el instrumento de fuerzas elementales ( hechicería).
V. Tomberg

[Alerta Mundial @AlertaMundoNews]

🇳🇱🇵🇸 | Manifestación masiva pro-Palestina en Ámsterdam, Países Bajos.

[El Doomer @El_Doomer]

Hay algo que los poderosos jamás le podrán quitar a un ser humano. Te pueden dejar sin agua, sin comida, sin electricidad. Incluso te pueden quitar la vida misma, y lo seguirás conservando. Es la dignidad.

Este hombre de Gaza nos da una lección sobre algo que parece que perdimos en Occidente hace mucho tiempo.

Tenemos de todo, pero nos falta lo más importante: empatía, pensamiento crítico, dignidad y compás moral. O lo recuperamos pronto, o pagaremos muy cara nuestra ignorancia e indiferencia en un mundo en claro declive cuyas crisis acaban de comenzar, y cuya dinámica de poder geopolítico está cambiando a pasos agigantados, empujándonos cada vez más hacia la irrelevancia mientras nos llenamos las manos de sangre.

Debemos parar esta carnicería y replantearnos seriamente si nos podemos seguir permitiendo un sistema que genera esta clase de situaciones y representantes políticos indignos, ignorantes y psicopáticos.

Aprendamos con humildad de alguien que lo ha perdido todo, pero que conserva lo más importante. Nunca más perdamos nuestra dignidad ni nuestra humanidad, porque sin ellas todo es para nada 👇

[Don Favs @Don_Favs]

Yo con 10 grados de miopía en cada ojo, caminando sin gafas en la calle.

[Turrón @He__dicho]

1 min 47 s de belleza. 😻

[Alvaro Cintas @dr_cintas]

The combination of Bing Chat vision with DALL•E 3 is amazing.

Bing not only understood my image but also brought my logo sketch to life using DALL•E 3.

Here is how you can do it too in a couple of minutes:

[Stable Diffusion 🎨 AI Art @DiffusionPics]

Just prompt travel and IPAdapters

animatediff-cli-prompt-travel

"prompt_map": {
"0": "upper_body, open_eyes, closed_mouth",
"16": "upper_body, closed_eyes, closed_mouth",
"32": "upper_body, open_eyes, closed_mouth",
"48": "upper_body, closed_eyes, closed_mouth",
"64": "upper_body, open_eyes, closed_mouth",
"80": "upper_body, closed_eyes, closed_mouth",
"88": "upper_body,  open_eyes, smile",
"96": "upper_body, open_eyes, smile, happy",
"104": "upper_body, closed_eyes, closed_mouth",
"112": "upper_body, open_eyes",
"120": "upper_body, open_eyes"
  },

[AI Breakfast @AiBreakfast]

3D Gaussian Splatting can turn photos into explorable worlds.

Stunning detail.

So much so that it gives merit to the simulation hypothesis.

[Alexandre Devaux @AlexandreDevaux]

3D Gaussian Splatting is really impressive 🙂
Pushing some test here with 25 photos as input and only 10000 iterations.
Hair, eyelashes are incomparable to photogrammetry.
I'll bench against NeRF a bit more in detail soon!

[Linus ✦ Ekenstam @LinusEkenstam]

What did I just watch?

Star Wars x AI

Mind blown, creative humans using AI to dream up a very different Star Wars.

By @douggypledger & @osymyso

[La propia nubesita @EfedeF]

@Perroacuadros Hay que irles a dar una paloterapia a este par de calvos hijueputas

[Bilawal Sidhu @bilawalsidhu]

This is kinda what I want generative fill for 3D scenes to feel like.

Imagine specifying the type of content to fill (river, village, road etc), or pulling in a 3D scan and in-painting the rest.

Amazing shader work by @1000___Words

[Massimo @Rainmaker1973]

The Mandelbulb is a 3-dimensional fractal: since a canonical 3-dimensional Mandelbrot set does not exist, it is possible to construct Mandelbrot sets in 4 dimensions using quaternions & bicomplex numbers

[📹 Disney Animation]

[Muzzammil @DevMuzzammil]

This is the most advanced use of AI

[Lior Alexander @LiorOnAI]

Impressive. GigaGAN is a 1B-parameter GAN that can scale 36 times larger than StyleGAN.

The model from Adobe/CMU proves that proves that GANs can be scaled to large datasets AND remain stable.

Features:
▸ Latent Space Editing: supports latent interpolation, style mixing, and vector arithmetic operations.

▸ Speed: It can produce 512px images in 0.13 seconds and 4K images in 3.66 seconds.

▸ Upsampling: it can be used as upsampler for ultra-high-resolution images.

[Espíritu de Autodisciplina @autodisciplinas]

Entrenamiento Cristiano Ronaldo.

Haz estos 10 ejercicios todos los días para construir un cuerpo estético

1.