Closed lawrencecchen closed 1 year ago
Just read stable diffusion's source code and learned that the tokenizer also caps at 77 tokens, so this issue is moot. I would still love to know why this is the case though!
@lawrencecchen this explains it: https://github.com/divamgupta/stable-diffusion-tensorflow/issues/20#issuecomment-1253779733
The clip-vit-large-patch14 (https://huggingface.co/openai/clip-vit-large-patch14) model used by SD can only handle sequences of 77 tokens. It works like that in the original pytorch implementation as well. Anything longer than that gets silently truncated.
Is there any way to have longer prompts? (I'm a complete ML noob, would love to learn!)