Tag
A tweet showing a trick of handing a floor plan to AI and having it directly generate a 3D render in a specified style (e.g., Kyoto style), reflecting the power of current 3D generation models.
Adobe's experimental iOS camera app Project Indigo adds AI features including LLM-powered photo critique and editing suggestions, advanced object removal, depth-of-field generation, and style transfer.
Introduces two open-source AI writing skill templates that mimic Liu Run's business analysis style and Luo Zhenyu's quote style, enabling AI to produce professional and shareable articles, lowering the barrier to writing.
Krea 2 is a series of foundation models for creative image generation, built with a large-scale data infrastructure and multi-stage training pipeline. It introduces a prompt expander and style-reference system to improve steerability and enable creative exploration.
FreeStyle proposes a scalable dual-reference generation framework using community LoRA mining to construct large-scale style-content triplets, with disentanglement mechanisms to prevent content leakage, and introduces a comprehensive benchmark for evaluation.
The author reflects on a senior's journey from following Andrew Ng's courses four years ago to publishing papers in top journals today, and cites a blog post explaining style transfer with a PyTorch implementation.
Reloop Animation Studio lets users transform video ideas into Pixar, Clay, or Manga styles.
Tencent releases MegaStyle, a large-scale open-source style transfer model with full training/inference code, 1.4M dataset, and pre-trained models.
AutoFigure-Edit generates editable scientific illustrations from text descriptions and reference images, enabling flexible style adaptation and efficient refinement.