Skip to content

Conversation

@azmenak
Copy link

@azmenak azmenak commented Mar 26, 2025

Updates CUDA to MPS/CPU as needed

Manage to get this running on my local machine (M4 Max 128BG)

Takes ~500s to run with:

  • 1024x1024 input image
  • steps: 30
  • guidance: 3.5
  • conditioning scale: 1
  • guidance start: 0
  • guidance end: 1
  • model version: aes_stage2

craigstjean and others added 4 commits March 24, 2025 14:16
Added checks for MPS and corrected usages of .cuda()

Note, not using MPS for facexlib or insightface as they
don't currently support it.
@EndlessSora EndlessSora force-pushed the main branch 8 times, most recently from 0c1fa9e to 7e7faf3 Compare April 16, 2025 21:27
@EndlessSora EndlessSora force-pushed the main branch 2 times, most recently from 09104be to aaa6ea5 Compare August 22, 2025 21:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants