You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
NoiseScheduler https://github.com/keras-team/keras-cv/blob/master/keras_cv/models/stable_diffusion/noise_scheduler.py contains a bug with default parameters. For a pretrained SD it must be: NoiseScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule='scaled_linear', clip_sample=False). For now it is: NoiseScheduler(beta_start=0.0001, beta_end=0.02, beta_schedule='linear', clip_sample=True). As I understand it, this happened because of copy-paste with a hugging face (where the default parameters are taken for some old GANs).
The text was updated successfully, but these errors were encountered:
It can be obtained from huggingface's diffusers like that : from diffusers import DDIMScheduler scheduler = DDIMScheduler.from_pretrained('runwayml/stable-diffusion-v1-5', subfolder='scheduler') print(scheduler)
NoiseScheduler https://github.com/keras-team/keras-cv/blob/master/keras_cv/models/stable_diffusion/noise_scheduler.py contains a bug with default parameters. For a pretrained SD it must be: NoiseScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule='scaled_linear', clip_sample=False). For now it is: NoiseScheduler(beta_start=0.0001, beta_end=0.02, beta_schedule='linear', clip_sample=True). As I understand it, this happened because of copy-paste with a hugging face (where the default parameters are taken for some old GANs).
The text was updated successfully, but these errors were encountered: