Open y0ur5h4d0w opened 1 year ago
Check the checkpoint file: if you copied the url and used wget or similar, you end up with an html file (open in a text editor to check). You need to click the link and download the file through a web browser. It just seems to be a dumb huggingface thing.
@drCJH I met the same probelm, but i have downloaded the file through web browser, the same error occurs again.
hi all1 i've been thinkering the whole day in order to have the AI working on my ubuntu 23.04 laptop, right now i'm at the point where i get some errors i can't understand, these errors are the followings, is there anyone who can help me understand how to proceed? if you need any more informations just tell me!
OS: Ubuntu Linux 23.04 python version: 3.10.10 miniconda: latest, just downloaded
installed the requirements.txt already and got to the point you see down here ^^" thanks for the help!
(base) y05h@DarkLand:~/AI_STUFF/stablediffusion-main$ python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt /home/y05h/AI_STUFF/stable-diffusion-2-1/v2-1_768-ema-pruned.ckpt --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768
main (opt)
File "/home/y05h/AI_STUFF/stablediffusion-main/scripts/txt2img.py", line 220, in main
model = load_model_from_config(config, f"{opt.ckpt}", device)
File "/home/y05h/AI_STUFF/stablediffusion-main/scripts/txt2img.py", line 31, in load_model_from_config
pl_sd = torch.load(ckpt, map_location="cpu")
File "/home/y05h/miniconda3/lib/python3.10/site-packages/torch/serialization.py", line 713, in load
return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args)
File "/home/y05h/miniconda3/lib/python3.10/site-packages/torch/serialization.py", line 920, in _legacy_load
magic_number = pickle_module.load(f, pickle_load_args)
_pickle.UnpicklingError: invalid load key, 'v'.
Global seed set to 42 Loading model from /home/y05h/AI_STUFF/stable-diffusion-2-1/v2-1_768-ema-pruned.ckpt Traceback (most recent call last): File "/home/y05h/AI_STUFF/stablediffusion-main/scripts/txt2img.py", line 389, in