all_code_base / lrm /flux /docs /migration_notes.md
aryadomain's picture
Add files using upload-large-folder tool
b4efe93 verified
|
Raw
History Blame Contribute Delete
768 Bytes

Migration Notes (SDXL -> Flux)

Reused As-Is

  • Trainer loop structure
  • Accelerator stack and checkpoint flow
  • Pairwise criterion math and evaluation logic
  • Dataset filtering and pseudo-preference pipeline

Flux-Specific Changes

  • Base model switched to FLUX.1-schnell.
  • Diffusion UNet path replaced with Flux transformer token path.
  • Latent handling changed to packed latents + latent image ids.
  • Second tokenizer switched from CLIP tokenizer to T5 tokenizer.

Config Changes

  • step_flux_base now points to Flux checkpoints.
  • guidance_scale default set to 0.0.
  • Removed SDXL-only model fields from Flux run config.

Smoke Test Policy

  • Use /home/user/aev/bin/python for checks.
  • Start with syntax/import smoke tests before full training launch.