Step1X-3D is an open-source framework by StepFun AI for high-fidelity and controllable generation of textured 3D assets from text or image prompts. The project addresses key challenges in 3D generation through a rigorous data curation pipeline that processes over 5 million assets to produce a 2 million high-quality dataset with standardized geometric and textural properties. The architecture uses a two-stage 3D-native approach combining a hybrid VAE-DiT geometry generator with an SD-XL-based texture synthesis module. A key innovation is bridging 2D and 3D generation paradigms by supporting direct transfer of 2D control techniques such as LoRA to 3D synthesis, enabling fine-grained style and content control. The framework generates 3D assets with high-fidelity geometry and versatile texture maps while maintaining exceptional alignment between surface geometry and texture mapping. Step1X-3D provides full open-source release of models, training code, and adaptation modules, making it accessible for research and production workflows. The project supports both text-to-3D and image-to-3D generation modes with controllable parameters for mesh quality and texture resolution.