Skip to content

[Community Pipelines] LPW Pipeline on Diffusers 0.8.0 #1616

@WASasquatch

Description

@WASasquatch

Describe the bug

Why is current changes to diffusers effecting past versions? I suddenly can't use LPW on 0.8.0.

[/usr/local/lib/python3.8/dist-packages/diffusers/pipeline_utils.py](https://localhost:8080/#) in from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
    657         elif len(missing_modules) > 0:
    658             passed_modules = set(list(init_kwargs.keys()) + list(passed_class_obj.keys()))
--> 659             raise ValueError(
    660                 f"Pipeline {pipeline_class} expected {expected_modules}, but only {passed_modules} were passed."
    661             )

ValueError: Pipeline <class 'diffusers_modules.git.lpw_stable_diffusion.StableDiffusionLongPromptWeightingPipeline'> expected {'unet', 'safety_checker', 'text_encoder', 'feature_extractor', 'requires_safety_checker', 'scheduler', 'vae', 'tokenizer'}, but only {'unet', 'safety_checker', 'text_encoder', 'feature_extractor', 'scheduler', 'vae', 'tokenizer'} were passed.

Reproduction

Use LPW pipe on diffusers 0.8.0

pipe = DiffusionPipeline.from_pretrained(model_id, custom_pipeline="lpw_stable_diffusion", cache_dir=model_cache, torch_dtype=torch.float16, use_auth_token=TOKEN).to(device)

https://rebrand.ly/easy-diffusion

Logs

No response

System Info

  • diffusers version: 0.8.0
  • Platform: Linux-5.10.133+-x86_64-with-glibc2.27
  • Python version: 3.8.16
  • PyTorch version (GPU?): 1.13.0+cu116 (True)
  • Huggingface_hub version: 0.11.1
  • Transformers version: 4.25.1
  • Using GPU in script?: Yes
  • Using distributed or parallel set-up in script?: No

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workingstaleIssues that haven't received updates

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions