sdxl相关问题

[Lil-CC]

按SDXL.md完成模型下载后，运行sdxl.py文件时对输入文本做了77的截断，后将stable-diffusion/text_encoder/config.json中"max_position_embeddings"改为248，报错如下
RuntimeError: Error(s) in loading state_dict for CLIPTextModel:
size mismatch for text_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([77, 1024]) from checkpoint, the shape in current model is torch.Size([248, 1024]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.
请问是需要修改text_encoder/config.json中的"architectures": ["CLIPTextModel"]吗？

[beichenzbc]

您好，如果按照我们SDXL.md的要求进行配置后，无需修改任何参数就可以运行python sdxl.py实现248长度的文生图了