OSError: (random module) does not appear to have a file named model_index.json.

[tin2tin]

Describe the bug

Using this example:

from diffusers import StableDiffusionControlNetImg2ImgPipeline, ControlNetModel, UniPCMultistepScheduler
import torch

controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, use_safetensors=True)
pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
).to("cuda")

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
output = pipe(
    "lego batman and robin", image=image, control_image=depth_map,
).images[0]

From:
https://huggingface.co/docs/diffusers/main/en/using-diffusers/controlnet#image-to-image

Throws this error:

OSError: lllyasviel/control_v11f1p_sd15_depth does not appear to have a file named config.json.

Reproduction

Run the code from the documentation example above.

Logs

No response

System Info

Win 11

Who can help?

@sayakpaul @yiyixuxu @DN6 @patrickvonplaten @stevhliu

[tin2tin]

Same this with:
Entry Not Found for url: https://huggingface.co/lllyasviel/sd-controlnet-canny/resolve/main/model_index.json.
Entry Not Found for url: https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/resolve/main/model_index.json
And there are properly more of the lllyasviel not working.

[DN6]

Hi @tin2tin I'm unable to reproduce this issue.

I took a look at the controlnet repo and it does have the config.json file
https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/tree/main

The config.json files for scribble and canny are
https://huggingface.co/lllyasviel/control_v11p_sd15_scribble/blob/main/config.json
https://huggingface.co/lllyasviel/control_v11p_sd15_canny/blob/main/config.json

[tin2tin]

It is looking for them in "resolve" and not "blob".
Ex. Entry Not Found for url: https://huggingface.co/lllyasviel/sd-controlnet-canny/resolve/main/model_index.json.

[DN6]

I don't think those model repos have model_index.json files and the URL for the config file is
https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/raw/main/config.json

[patrickvonplaten]

@tin2tin

The following code snippet works just fine:

from diffusers import StableDiffusionControlNetImg2ImgPipeline, ControlNetModel, UniPCMultistepScheduler
import torch

controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, use_safetensors=True)
pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16, use_safetensors=True
).to("cuda")

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

[yiyixuxu]

@tin2tin
let me know if you still experience any issue!

YiYi

[tin2tin]

Yes, there is still something wonky going on. I wonder if it is because I'm downloading locally on my computer I see this error, as compared to downloading on hf?

I've tried to clean out everything on my computer and install everything again, but those errors persist.

[tin2tin]

After updating Diffusers to the latest and running this code: #5632 (comment) I get this error:

Error: Python: Traceback (most recent call last):
  File "C:\Users\45239\AppData\Roaming\Python\Python310\site-packages\diffusers\configuration_utils.py", line 370, in load_config
    config_file = hf_hub_download(
  File "C:\Users\45239\AppData\Roaming\Python\Python310\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
  File "C:\Users\45239\AppData\Roaming\Python\Python310\site-packages\huggingface_hub\file_download.py", line 1340, in hf_hub_download
    raise LocalEntryNotFoundError(
huggingface_hub.utils._errors.LocalEntryNotFoundError: Cannot find the requested files in the disk cache and outgoing traffic has been disabled. To enable hf.co look-ups and downloads online, set 'local_files_only' to False.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\45239\Documents\unet_01.blend\Text.002", line 4, in <module>
  File "C:\Users\45239\AppData\Roaming\Python\Python310\site-packages\diffusers\pipelines\auto_pipeline.py", line 325, in from_pretrained
    config = cls.load_config(pretrained_model_or_path, **load_config_kwargs)
  File "C:\Users\45239\AppData\Roaming\Python\Python310\site-packages\diffusers\configuration_utils.py", line 397, in load_config
    raise EnvironmentError(
OSError: SimianLuo/LCM_Dreamshaper_v7 does not appear to have a file named model_index.json.

It seems like AutoPipelineForText2Image is able to find that file, but AutoPipelineForImage2Image isn't able to find it...?

[tin2tin]

Closing. This was a local issue.