How to use lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA-8B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-8B-Instruct") model = PeftModel.from_pretrained(base_model, "lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA-8B")
Hey!
Great effort team, nice!Was wondering if you are planning to pursue the Ref2VA one as well or in addition to the one you just released? Looking forward to your answer!
Best,Oliver
· Sign up or log in to comment
