I made a pipeline that lets you use any number of models at once

[alexblattner]

Model/Pipeline/Scheduler description

Here's how to do it: from rubberDiffusers import StableDiffusionRubberPipeline pipe=StableDiffusionRubberPipeline.from_pretrained( "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float32,local_files_only=True,safety_checker=None, requires_safety_checker=False, )

pipe2=StableDiffusionRubberPipeline.from_pretrained( "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float32,local_files_only=True,safety_checker=None, requires_safety_checker=False, )

apply_multiModel(pipe) pipe.added_model=[pipe2] image=pipe("your prompt",width=512,height=512,pos=["0:0-512:512"],mask_strengths=[.5],model_kwargs=[{prompt="your prompt for the first loaded model"}]).images[0]

Open source status

• [ ] The model implementation is available.
• [ ] The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

https://github.com/alexblattner/RubberDiffusers

[bghira]

is it a proposal or issue? maybe better for Show & Tell Discussion section

[alexblattner]

@bghira neither, it already exists and works

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.