Tag
This article analyzes ChatGPT's image editing feature, arguing that it performs full-frame regeneration via DALL-E rather than localized editing, based on network traffic and metadata evidence.
A personal reflection on the rapid evolution of AI over the past three years, from early ChatGPT and GPT-4 quotas to BabyAGI, DALL·E, and voice cloning.
OpenAI announces DALL·E API is now available in public beta, allowing developers to integrate image generation capabilities directly into their applications. Early adopters include Microsoft, CALA, and Mixtiles, with built-in safety features and content moderation.
OpenAI removes the waitlist for DALL·E beta, making the text-to-image generation tool immediately available to all users. The announcement reveals 1.5M+ active users creating 2M+ images daily, with plans to expand DALL·E API access to developers.
OpenAI introduces Outpainting for DALL·E, enabling users to extend generated or uploaded images to create large-scale images in any aspect ratio while maintaining visual consistency with shadows, reflections, and textures.
OpenAI's DALL·E image generation system is now available in public beta, inviting 1 million users from the waitlist with free monthly credits and optional paid plans. Users gain full commercial rights to generated images and can use features like editing, variations, and collections.
This article explains the architecture of DALL-E, focusing on its transformer component that correlates language with discrete image representations to generate high-quality images from text prompts.
An educational blog post explaining the Vector Quantized Variational Autoencoder (VQ-VAE) architecture, a key component of OpenAI's DALL-E image generation model.
OpenAI introduces DALL·E, a 12-billion parameter transformer model that generates images from text descriptions by treating text and images as a single token stream. The model demonstrates diverse capabilities including creating anthropomorphized objects, combining disparate concepts, rendering text, and performing image inpainting tasks.