baojudezeze/Qwen-dpo: Training code for Diffusion-DPO applied to the Qwen Image-2512 model. This implementation builds on the training framework provided by zk1009 and follows the methodology described in the paper “Diffusion Model Alignment Using Direct Preference Optimization”.

Training code for Diffusion-DPO applied to the Qwen Image-2512 model. This implementation builds on the training framework provided by zk1009 and follows the methodology described in the paper “Diffusion Model Alignment Using Direct Preference Optimization”.

Read Original

Related