Provide a way to find out which model branches map to which pipelines

[antoche]

Right now a model repo may have multiple branches (e.g., main, fp16, bf16, etc).

There seems to be a de facto convention that a given branch is designed for a specific purpose. E.g., The "main" branch contains the model weights with fp32 precision for a pytorch model, whereas the fp16 contains the same weights in fp16 precision.

Thus, if I see a "bf16" branch, I would be led to believe that I can get bf16-precision weights for my pytorch model for this branch. But if I try this, I get an error:

OSError: Error no file named diffusion_pytorch_model.bin found in directory .../datasets/huggingface/diffusers/models--stabilityai--stable-diffusion-2-1/snapshots/8d0c902020b6347a7f6d10420bb5e1bf57ff129e/unet.

And looking closer at the files in that branch, it is evident that they are actually destined for a flax model and nothing else. I should have used a FlaxStableDiffusionPipeline instead of a StableDiffusionPipeline. But I could not have known that before trying to instantiate the pipeline.

This seems to be yet another unstated convention, and there is no way of knowing what model&revision will work with what pipeline class other than brute-force trying every combination.

It would be great to have a way of figuring out what each branch is designed for, either via an explicit rule or an API call.

[patrickvonplaten]

Hey @antoche great observation! We're actually going to deprecate using revision=... very soon and instead will make use of variant=... as described here: #2305

We'll then have all files in the "main" branch which should be much more user-friendly. Let me know what you think? :-)

Note that we'll only make this change in like 1 month to give users enough time to update the diffusers version.

[antoche]

Great, do you prefer me to comment here or on #2305?

[patrickvonplaten]

Commenting here would be great :-)

[github-actions]

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.