OpenAI has integrated its latest image generation model, powering GPT-4o, into its API, allowing developers to incorporate high-quality image creation into their applications. This model demonstrates enhanced capabilities in rendering text, following complex prompts with numerous objects, and maintaining consistency across iterative refinements. Google Research has also introduced PASTA, a reinforcement learning agent that collaborates with users through conversational refinement to generate images tailored to individual preferences, utilizing a novel user simulation technique for training. AI
Summary written by None from 3 sources. How we write summaries →
RANK_REASON OpenAI released a natively multimodal model with advanced image generation capabilities into their API, and Google Research published a paper on a novel image generation agent.
