pljj315

i have modify and train base on dinov2, here is the code u can reference: https://github.com/pljj315/instant_id.git

> Running this code I got two correct images, > > ```python > from diffusers import HunyuanDiTPipeline > import torch > pipe = HunyuanDiTPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-Diffusers", torch_dtype=torch.float16) > pipe.to('cuda') > pipe.enable_model_cpu_offload() >...

> > Without training code we will not know how the model is trained. > > But if you use L in training, you must use L in inferring maybe...