InvokeAI/ldm/models
Lincoln Stein 943616044a Merge branch 'switch-ksampler-noise-scheduler-adaptively' into development
- This sets a step switchover point at which the k-samplers stop using the
  Karras noise schedule and start using the LatentDiffusion noise schedule.
  The advantage of this is that the Karras schedule produces excellent
  results at low step counts but starts to become unstable at high
  steps.

- A new command argument --karras_max, lets the user set where the
  switchover occurs. Default is 29 steps (1-29 steps Karras),
  (30 or greater LDM)

- Tildebyte, sorry to do a fast forward three-way merge for this
  but rebasing was just too painful due to extensive recent
  changes to the diffuser code.
2022-10-27 16:11:26 -04:00
..
diffusion Merge branch 'switch-ksampler-noise-scheduler-adaptively' into development 2022-10-27 16:11:26 -04:00
autoencoder.py start support for 1.5 inpainting model, not complete 2022-10-25 00:30:48 -04:00