Alpha-VLLM / Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation
MIT License
1.82k stars 74 forks source link

conrolnet support? #59

Open universewill opened 2 weeks ago

universewill commented 2 weeks ago

conrolnet support? Can lumina trained with input conditional images and generate image with image conditions like controlnet?

gaopengpjlab commented 2 weeks ago

We are actively exploring how to add image conditioning over DiT architecture. We will share our results once we finished our training.