OSError: None is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

1

Hi! i have one more problem with AI moels. Now python complains about that i don’t have access to huggingface repository. I don’t know why it happens, i run models locally.

I have next error:

OSError: None is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `token` or log in with `huggingface-cli login`.

Code

import torch
from controlnet_aux import CannyDetector
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
from diffusers.utils import load_image, make_image_grid
import os

MMIX_MODEL_PATH = os.getenv('MMIX_MODEL_PATH')
IP_ADAPTER_PATH = os.getenv('IP_ADAPTER')
CANNY_MODEL_PATH=os.getenv('CANNY_MODEL')

img1 = 'C:\\image-4.png'
img2 = 'C:\\image-3.png'


controlnet = ControlNetModel.from_pretrained(
    CANNY_MODEL_PATH,
    torch_dtype=torch.float16
    #varient="fp16"
)


pipe = StableDiffusionControlNetPipeline.from_pretrained(
    MMIX_MODEL_PATH,
    controlnet=controlnet,
    torch_dtype=torch.float16)


pipe.load_ip_adapter(
                     IP_ADAPTER_PATH,
                     subfolder="models",
weight_name="ip-adapter_sd15.bin"
)


ip_adap_img = load_image(img2)
img = load_image(img1).resize((768, 768))

canny = CannyDetector()
canny_img = canny(img, detect_resolution=512, image_resolution=768)


prompt = """(photorealistic:1.2), raw, masterpiece, high quality, 8k, girl wearing hoodie, headphones, hands in pocket"""
negative_prompt = "low quality, ugly, mutated"

pipe.set_ip_adapter_scale(0.5)

images = pipe(prompt = prompt,
              negative_prompt = negative_prompt,
              height = 768,
              width = 768,
              ip_adapter_image = ip_adap_img,
              image = canny_img,
              guidance_scale = 6,
              controlnet_conditioning_scale = 0.7,
              num_inference_steps = 20
              ).images[0]
2

Check your env variables as I assume these are not set:

import os

MMIX_MODEL_PATH = os.getenv('MMIX_MODEL_PATH')
print(MMIX_MODEL_PATH)
# None
3

Thanks. I checked my code and realized that I forgot to add load_dotenv()
I would also be grateful if you could look at my other problem related to inpainting.