Pipelines issue

[kalechinees]

Not too sure why this is happening. Everything installed accordingly but the "Generate" fetches 15 files, the GPU spins up and then I get the log below. Both stable-diffusion-v1-4 and 1-5 have been cloned through Huggingface.co and User Access token is pasted in the application. Do I need to edit something to point towards the .ckpt model of Stable-Diffusion 1.4?

Fetching 15 files: 100%|█████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 7505.91it/s] The config attributes {'clip_sample': False} were passed to PNDMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. Traceback (most recent call last): File "C:\AI\UnstableFusion\unstablefusion.py", line 897, in handle_generate_button if type(self.get_handler()) == ServerStableDiffusionHandler: File "C:\AI\UnstableFusion\unstablefusion.py", line 460, in get_handler return self.stable_diffusion_manager.get_handler() File "C:\AI\UnstableFusion\unstablefusion.py", line 329, in get_handler return self.get_local_handler(self.get_huggingface_token()) File "C:\AI\UnstableFusion\unstablefusion.py", line 312, in get_local_handler self.cached_local_handler = StableDiffusionHandler(token) File "C:\AI\UnstableFusion\diffusionserver.py", line 36, in init self.text2img = StableDiffusionPipeline.from_pretrained( File "C:\Users\Jeff\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipeline_utils.py", line 516, in from_pretrained raise ValueError( ValueError: The component <class 'transformers.models.clip.image_processing_clip.CLIPImageProcessor'> of <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_config', 'from_config'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained']}.

[WhiteCodeC]

How did you manage to start the image generation? when i try it returns

 eprint(line:60) :: Error when calling Cognitive Face API:
        status_code: 401
        code: 401
        message: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.

[ahrm]

I assume the original issue is because of library version incompatibility. Make sure you have the same versions specified in requirements.txt.

How did you manage to start the image generation? when i try it returns

You need to enter your huggingface token when asked (after accepting the license agreement in stable diffusion model page).

[worldemar]

this still can be reproduced by installing from requirements.txt into venv, tested on python 3.9.0 and python 3.11.0, the diffusers package is exactly as specified in txt.

[worldemar]

Installing transformers==4.22.1 which is specified in UnstableFusionServer.ipynb (requirements.txt suggests newer version via >=) seem to solve the issue