Seunghyun JiandClaude Opus 5.5 6e207b2b45 Support the PiD v1.5 flux2 checkpoint (MOSS-Image / FLUX.2 latents), 0.3.0 ...

The flux2 student takes the packed, BatchNorm-normalized (B,128,H/16,W/16)
latent as is and unpatchifies it 2x2 inside the LQ projection (upstream
PID_SR4X_V1PT5_FOR_FLUX2). Same prompt prefix and 4-step schedule as
qwenimage, so the bundled null caption carries over.

- pid_net: latent_unpatchify_factor
- pid_core: flux2 kwargs, family detected from the first LQ conv's input
  width (16 / 32), output scale read from the net (32 / 64 px per cell),
  128-ch latents passed through unnormalized, family mismatch raises
- loader: "(auto-download) flux2 / MOSS-Image"; the bare "(auto-download)"
  stays qwenimage. Downloads go to the first registered pid folder
  (extra_model_paths.yaml first) and skip a checkpoint already present in
  any of them
- decode: tile_latent / tile_overlap keep their 32-px unit across families;
  use_calib is ignored for flux2

Checked on two MOSS cached latents: clean load (0 missing / 0 unexpected),
area-downsampled output 31.6 / 34.7 dB PSNR against the FLUX.2 VAE decode,
8.2 GB peak with 2048 px tiles.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-11-03 22:19:22 +09:00

1.1 MiB

Raw History

View Raw