zhenyuw16 / GenArtist

Code release for our NeurIPS 2024 Spotlight paper "GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing"
81 stars 6 forks source link

Code for interacting with MLLM #3

Open Qrteng opened 4 months ago

Qrteng commented 4 months ago

Thank you for presenting such awesome work! I noticed that the code provided seems to be a simplified version compared to what you described in the paper. Specifically, the automatic image generation and editing process conducted by MLLM as an agent are not present in the code, such as the decomposition step, tree generation, self-correction and editing.

Could you please clarify if these parts will be released in the future? If I have misunderstood something, please let me know. Thank you very much for your assistance!