Multimodal-LLM Agent For Text-Driven Multi-Attribute Face Editing

Facial attribute editing aims to manipulate specific attributes of a face image while the other attributes are not affected. The development of models like StyleGAN and CLIP has significantly advanced text-driven facial attribute editing. However, single models frequently struggle with complex textual descriptions involving multiple attributes, and the absence of verification and self-correction mechanisms, making the results unreliable. To address these challenges, we propose MMFE, a text-driven multi-attribute facial editing system. MMFE integrates various facial editing models and leverages a large language model (LLM) as an agent to select appropriate models based on natural language requests. Finally, a multimodal large language model (MLLM) is introduced for result verification. Our experiments demonstrate that MMFE significantly improves performance in text-driven multi-attribute facial editing tasks.