Member-only story
Your Daily AI Research tl;dr — 2022–08–11 🧠
The GitHub code is now available for stable diffusion (image generation model similar to Dalle) and CLIP-based Style Transfer for 3D Assets!
2 min readAug 11, 2022
Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.
1️⃣ CLIP-based Neural Neighbor Style Transfer for 3D Assets
A method for transferring the style from a set of images, like a painting style, to a 3D object, changing the texture appearance of the 3D asset.
Link to the paper: https://arxiv.org/pdf/2208.04370.pdf
2️⃣ High-Resolution Image Synthesis with Latent Diffusion Models
A latent text-to-image diffusion model.
Similar to Google’s Imagen, this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.
