@cosmic96336138 Profile picture

21

@cosmic96336138

Digital Artist & AIart

Similar User
Linnaxx photo

@linnaxx__

Contia photo

@contia_gr

Sal photo

@salgiudici

にゃんのすけ photo

@D_nyannosuke

🍁TAIWANMIA🍁 photo

@TAIWAN97210652

Thomas Knight photo

@KnightOfNook

Marcus Valles -

@Marcus_INVR

21 Reposted

Introducing Flux Tools 📸 3 different model types this time; Redux, Fill and Controlnets These models are designed to add control and steerability!

Tweet Image 1

21 Reposted

Sim Anything: Automated 3D Physical Simulation of Open-world Scene with Gaussian Splatting Contributions: • Sim Anything is the first to use MLLM for zero-shot physical property estimation of objects in 3D scenes. • We reformulate physical property estimation as a…


21 Reposted

📈 Bitcoin vient de passer les 98 000 $ !

Tweet Image 1

21 Reposted

🦜 JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation 🦙 Jupyter Notebook 🥳 Thanks to Xuyang Cao ❤ Guoxin Wang ❤ Sheng Shi ❤ Zhao Jun ❤ Yang Yao ❤ Jintao Fei ❤ Minyu Gao ❤ 🌐page:…


21 Reposted

🖼 In-Context LoRA for Diffusion Transformers 🔥 now on @tost_ai, @runpod_io, @ComfyUI and @ProjectJupyter 🥳 Thanks to @xuangen_hlh ❤ Wei Wang ❤ Zhi-Fan Wu ❤ Yupeng Shi ❤ Huanzhang Dou ❤ Chen Liang ❤ Yutong Feng ❤ Yu Liu ❤ Jingren Zhou ❤ 🌐page:…

Introducing our new work: In-Context LoRA. Project page: ali-vilab.github.io/In-Context-LoR…

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4


21 Reposted

Have you ever seen a swarm of ferals, traveler? Not like the group we pushed off back at the Hadron Gap - a proper swarm. A "blot out the sun" swarm. A "make your peace" swarm. The individual ferals, the ones disconnected from their hive, they're harmless. They've got guns, sure…

Tweet Image 1

21 Reposted

C’est chaud, très chaud: Le navire chinois Yi Peng 3 a été poursuivi, intercepté et arraisonné par le navire de la marine danoise Y311 Søløven après que le navire chinois ait détruit deux câbles de télécommunications sous-marins reliant la Finlande à l'Allemagne et la Suède à la…

BREAKING: The Chinese vessel Yi Peng 3 has been chased, intercepted, and boarded by Danish Navy vessel Y311 Søløven after the Chinese vessel destroyed 2 undersea telecom cables linking Finland-Germany and Sweden-Lithuania. The vessel sailed from Russia & the captain is Russian

Tweet Image 1


21 Reposted

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes. research.nvidia.com/labs/dir/edify…


21 Reposted

MVideo can generate long videos with smooth actions by using mask sequences for motion control! mvideo-v1.github.io


21 Reposted

Bitcoin to $100,000+ Dogecoin to $1.00+ SEND IT 🚀

Tweet Image 1

21 Reposted

Some early testing of this opensourced "Act-1" There are so many knobs to turn and test but it's incredibly promising I can get it better still this is just a couple hours of tickering - I want 1:1 expression transfer. Stay tuned!


21 Reposted

DimensionX can generate photorealistic 3D and 4D scenes from a single image! It supports camera controls for video generation and can rerender videos from different angles. Links ⬇️


21 Reposted

🚀 👀 Flux 1.1 Ultra Pro + Upscale on Scenario. 👇


21 Reposted

FacePoke: Real-time facial animation control by @flngr on @huggingface Upload a portrait → adjust head position, eyes, mouth & expressions in real-time → quickly change character expressions & poses in static images Link below. I tried it on my uploaded image:


21 Reposted

Nvidia presents LLaMA-Mesh Unifying 3D Mesh Generation with Language Models


21 Reposted

I ported X-Portrait to ComfyUI! 🔥 Generate performances for any character. It performs well with certain styles and input videos but comes up short in a lot of ways (X-Portrait 2 soon? 👀) Currently requires (>20GB VRAM) to run, I've been testing on a 4090. Repo link 👇


21 Reposted

Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction Contributions: • A method for efficiently reconstructing dynamic surfaces from multi-view videos using Gaussian surfels. • A unified and gradient-aware densification strategy for…


21 Reposted

ZIM can generate precise matte masks from segmentation labels, enabling zero-shot image matting! Links ⬇️


21 Reposted

Incentives matter. There should be rewards for wise spending, but those who waste taxpayer funds cannot be allowed to keep doing so without consequences.

Elon Musk said: “If a government official is effective in spending your money, they should be rewarded. If they waste your money, they should be fired.”

Tweet Image 1


Loading...

Something went wrong.


Something went wrong.