DreamScene is a novel text-to-3D scene generation framework that addresses the challenges of maintaining high quality, consistency, and editing flexibility in text-to-3D generation. The framework employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to generate fast, semantically rich, and high-quality representations. FPS uses 3D Gaussian filtering for optimization stability and leverages reconstruction techniques to generate plausible textures. Additionally, DreamScene uses a progressive three-stage camera sampling strategy to ensure object and environment integration and scene-wide 3D consistency. The framework also enhances scene editing flexibility by integrating objects and environments, enabling targeted adjustments. Extensive experiments validate DreamScene's superiority over current state-of-the-art techniques, demonstrating its potential for diverse applications. The framework is implemented with a combination of diffusion models and 3D Gaussian splatting, and it is capable of generating scenes with up to 20 objects. DreamScene's approach significantly improves the efficiency and quality of text-to-3D generation, offering a flexible and consistent solution for creating detailed 3D scenes.DreamScene is a novel text-to-3D scene generation framework that addresses the challenges of maintaining high quality, consistency, and editing flexibility in text-to-3D generation. The framework employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to generate fast, semantically rich, and high-quality representations. FPS uses 3D Gaussian filtering for optimization stability and leverages reconstruction techniques to generate plausible textures. Additionally, DreamScene uses a progressive three-stage camera sampling strategy to ensure object and environment integration and scene-wide 3D consistency. The framework also enhances scene editing flexibility by integrating objects and environments, enabling targeted adjustments. Extensive experiments validate DreamScene's superiority over current state-of-the-art techniques, demonstrating its potential for diverse applications. The framework is implemented with a combination of diffusion models and 3D Gaussian splatting, and it is capable of generating scenes with up to 20 objects. DreamScene's approach significantly improves the efficiency and quality of text-to-3D generation, offering a flexible and consistent solution for creating detailed 3D scenes.