You can deploy this model and start earning money today!

Lanl11/
pMF-H-FDSIM-imagenet256-sigma07-4k

Name: pMF-H-FDSIM-imagenet256-sigma07-4k
Availability: InStock

Views

No views yet

pMF-H · FD-SIM · ImageNet-256 · σ0.7 @ 4000 steps

Class-conditional ImageNet-256 generator (pMF-H lineage), fine-tuned with FD-Loss (mmdx — Nyström-approximated MMD) on a 10-encoder gated-PID judge panel. This is the σ0.7 arm (RBF bandwidth = 0.7 × median heuristic), continued from the converged 10-encoder gated-PID run (step 3499) to step 4000.

This file

model.pth — model weights only (the non-EMA model state_dict).

field	value
tensors	654 (all `float32`)
size	3.82 GB
opt-step	4000 (`current_step`; `step`=3999, 0-indexed)
samples seen	20,480,000
source ckpt	`phase42-sigma07-from3499/step_0003999.pth` (model slice; EMA + optimizer + queues dropped)
resolution	256×256, class-conditional (1000 ImageNet classes)

Loading

The file is a torch checkpoint with the weights under the model key — drop-in for the MMDLoss/FD-Loss training repo's load_from:

yaml

# config
load_from: /path/to/model.pth

Or directly:

python

import torch
ckpt = torch.load("model.pth", map_location="cpu", weights_only=False)
state_dict = ckpt["model"]            # 654 tensors
model.load_state_dict(state_dict, strict=False)
print(ckpt["current_step"], ckpt["samples_seen"])  # 4000, 20480000

Notes

These are the raw (non-EMA) model weights. The EMA shadow weights and the optimizer state were intentionally excluded to keep this a slim inference artifact (the full 26.7 GB training checkpoint is resumable but not published here).
Generation in the source project uses 1-step sampling at cfg 7.0.

Lanl11/pMF-H-FDSIM-imagenet256-sigma07-4k

pMF-H · FD-SIM · ImageNet-256 · σ0.7 @ 4000 steps

This file

Loading

Notes

Lanl11/
pMF-H-FDSIM-imagenet256-sigma07-4k