TypeHost retweeted
All major neural networks, in one chart: https://xitter.cf/t.co/F6da67Gr3C
v/The Asimov Institute
TypeHost retweeted
We proposed UPainting to unify simple and complex scene image generation. The model integrates cross-modal guidance into a text-conditional diffusion model. UPainting outperforms other models in caption similarity & image fidelity. More details: upainting.github.io/
TypeHost retweeted
The @Gradio Demo for Naruto text to image is out on @huggingface Spaces by @LambdaAPI
demo: huggingface.co/spaces/lambda…
TypeHost retweeted
Introducing ERNIE-ViLG 2.0, a 24B text-to-image model with knowledge-enhanced Mixture-of-Denoising-Experts that obtains SOTA results on MS-COCO. This is also the largest text-to-image model at present.
Paper: arxiv.org/pdf/2210.15257.pdf
Demo @huggingface: huggingface.co/spaces/Paddle…
TypeHost retweeted
Introducing Turbopack, the successor to Webpack.
◆ ~700x faster than Webpack
◆ 10x faster than Vite
◆ Native incremental architecture built with Rust
◆ Support for React Server Components
◆ Support for TS, JSX, CSS & more
Now open-source in Alpha.
vercel.com/blog/turbopack
TypeHost retweeted
A Proof-of-Concept of an AI Assistant Designer using #UnrealEngine's #Metahuman, #stablediffusion, #OpenAI's Whisper and #GPT3.
TypeHost retweeted
"Although not alive, I can still create art": Ai-Da might just be a humanoid robot, but on Tuesday, it addressed U.K. lawmakers and told them what it can offer the world.
TypeHost retweeted
AI music generators could be a boon for artists — but also problematic ift.tt/rtkZmMq
TypeHost retweeted
We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts.
Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.
TypeHost retweeted
Lexica's search engine is now 100% powered by CLIP.
This means your search query will likely have thousands of matching Stable Diffusion images. You can also search by image similarity too, which is a rabbit hole I've fallen down one too many times.
lexica.art
TypeHost retweeted
Broadcom to Acquire VMware for Approximately $61 Billion in Cash and Stock
vmware.com/content/dam/digit…
TypeHost retweeted
3D知識ゼロの音楽ユニットが1年間勉強して、全編CGのMVを自主制作してみました!
撮影から編集まで、全ての工程を自宅のみで完結。
SF映画のような未来の世界を描いた作品です🪐
個人規模でも低予算でCG映像制作を楽しめる時代がもう来ています!
皆さんもレッツトライ💪
#UnrealEngine
#UE5
#3DCG
TypeHost retweeted
Our newest system DALL·E 2 can create realistic images and art from a description in natural language. See it here: openai.com/dall-e-2/
TypeHost retweeted
Head over to befores & afters for the interview with Haz Dulull from Hazimation. He reveals many insights about their pipeline using @UnrealEngine, @reallusion's Character Creator, @Xsens and iClone.
Learn more: https://xitter.cf/t.co/inTu4EyBQ2
TypeHost retweeted
🎉 Announcing: The PHP Foundation
🔗 opencollective.com/phpfounda…
ℹ️ More information at: blog.jetbrains.com/phpstorm/…
TypeHost retweeted
PyTorchVideo: A Deep Learning Library for Video Understanding
deepai.org/publication/pytor…
by Haoqi Fan et al. including @tulliemurrell
#OpenSource #PyTorch
TypeHost retweeted
Samsung invests in DigiLens XR glasses firm at valuation over $500M venturebeat.com/2021/11/04/s…
TypeHost retweeted
Microsoft joins Open Infrastructure Foundation zdnet.com/article/microsoft-…
TypeHost retweeted
@Innodata CPO, @Rsinghal11, sat down with @VentureBeat's @SageLazzaro to discuss how enterprises can best approach #data, launch #AI initiatives, mitigate bias & more. Read the full interview below! #DataForAI #ML #DataCentricAI
hubs.ly/H0W6mq90

























