How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces
A developer created an agent that builds a 3D Paris gallery by chaining two Hugging Face Spaces. The first Space, 'gaussian-splatting', generates 3D Gaussian splatting scenes from text prompts. The second Space, '3d-viewer', renders the generated scenes. The agent uses the Transformers Agents library to orchestrate the workflow, passing the output of the first Space as input to the second. This demonstrates how to combine multiple Spaces into a single application, enabling complex pipelines without manual intervention. The blog post provides a step-by-step guide, including code snippets and configuration details. The agent can be extended to other tasks, such as generating 3D models from images or combining Spaces for data processing.
Shows how to chain Hugging Face Spaces for multi-step AI workflows.