Stable diffusion text_to_image.py discussion

🧨 Diffusers
1

Hi!
I want to change
text_encoder = CLIPTextModel.from_pretrained(args.pretrained_model_name_or_path, subfolder=“text_encoder”, revision=args.revision) in text_to_image.py 464 line to torch.nn.Embedding(77, 768)

I don’t want to use CLIP embedding because this dataset is very special.

When i change this code, it ran this error.

image
image1925Ă—1142 273 KB

image
image1927Ă—1095 320 KB

what can i do?Thx

2

hey @barry556652 can you post a reproducible code snippet?