The paper presents six design principles for generative AI applications, addressing unique characteristics of generative AI and offering new interpretations of known issues in AI design. The principles support two user goals: optimizing generated artifacts to meet task-specific criteria and exploring possibilities within a domain. Each principle is paired with strategies for implementation through UX capabilities or design processes. The principles were developed through an iterative process involving literature review, feedback from design practitioners, validation against real-world applications, and incorporation into two generative AI applications. The paper also discusses related work in human-computer interaction and human-AI interaction, highlighting the need for new design guidelines due to the unique challenges and risks of generative AI. The six principles include Design Responsibly, Design for Mental Models, Design for Appropriate Trust & Reliance, Design for Generative Variability, Design for Co-Creation, and Design for Imperfection. The principles and strategies were validated through multiple iterations, including a modified heuristic evaluation of commercial generative AI applications. The paper concludes that these principles provide actionable guidance for designing generative AI applications that are safe, effective, and user-centered.The paper presents six design principles for generative AI applications, addressing unique characteristics of generative AI and offering new interpretations of known issues in AI design. The principles support two user goals: optimizing generated artifacts to meet task-specific criteria and exploring possibilities within a domain. Each principle is paired with strategies for implementation through UX capabilities or design processes. The principles were developed through an iterative process involving literature review, feedback from design practitioners, validation against real-world applications, and incorporation into two generative AI applications. The paper also discusses related work in human-computer interaction and human-AI interaction, highlighting the need for new design guidelines due to the unique challenges and risks of generative AI. The six principles include Design Responsibly, Design for Mental Models, Design for Appropriate Trust & Reliance, Design for Generative Variability, Design for Co-Creation, and Design for Imperfection. The principles and strategies were validated through multiple iterations, including a modified heuristic evaluation of commercial generative AI applications. The paper concludes that these principles provide actionable guidance for designing generative AI applications that are safe, effective, and user-centered.