search

tencent-ailab / IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Apache License 2.0
4.52k stars 298 forks source link

We couldn't connect to 'https://huggingface.co' #209

Closed gagbaghdas closed 6 months ago

gagbaghdas commented 6 months ago

Hey guys. I'm trying to run the training script , and it gives me the following error. 

OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like runwayml/stable-diffusion-v1-5/ is not the path to a directory containing a scheduler_config.json file.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Anyone have an idea what I'm doing wrong?

xiaohu2015 commented 6 months ago

maybe you can firstly download the model into local path

gagbaghdas commented 6 months ago

maybe you can firstly download the model into local path

Hey @xiaohu2015 . Is the v1-5-pruned.ckpt ok ?I've just downloaded it

xiaohu2015 commented 6 months ago 
from diffusers import StableDiffusionPipeline
import torch

model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.save_pretrained("local_path")
gagbaghdas commented 6 months ago

Thanks!!!

rafstahelin commented 6 months ago

Hey guys. I'm trying to run the training script , and it gives me the following error. 


OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like runwayml/stable-diffusion-v1-5/ is not the path to a directory containing a scheduler_config.json file.

Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Anyone have an idea what I'm doing wrong?

What's the training for?

gagbaghdas commented 6 months ago

@rafstahelin please see here