ShivamShrirao / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
https://huggingface.co/docs/diffusers
Apache License 2.0
1.89k stars 505 forks source link

Getting Error: signal: floating point exception (core dumped) when changing the scheduler #166

Open geekyayush opened 1 year ago

geekyayush commented 1 year ago

I am trying to change the scheduler of my dreambooth model in the inference call. But I am getting the following error when I do so:

Error: signal: floating point exception (core dumped)

Here's how I am trying to do it:

newScheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)

After following huggingface documentation

My model scheduler_config.json

{
  "_class_name": "DDIMScheduler",
  "_diffusers_version": "0.10.0",
  "beta_end": 0.012,
  "beta_schedule": "scaled_linear",
  "beta_start": 0.00085,
  "clip_sample": false,
  "num_train_timesteps": 1000,
  "prediction_type": "epsilon",
  "set_alpha_to_one": false,
  "steps_offset": 1,
  "trained_betas": null
}

I would really appreciate any help.