Downloads · 30 days
0
Roydon728/GenPolar
GenPolar is a image-to-image model from Roydon728. Use it when you need one image transformed into another. It is set up for diffusers.
Official model weights for GenPolar: Stokes-Informed Diffusion for Robust Linear Polarization Estimation.
Downloads · 30 days
0
Access
Public
Updated Jul 23, 2026
Repo size
9.8 GB
Likes
0
Public
Click a slice to open those files.
.pth9.8 GB · 100%
From the Hugging Face model README
Official model weights for GenPolar: Stokes-Informed Diffusion for Robust Linear Polarization Estimation.
GenPolar estimates the linear Stokes components from an intensity/RGB observation and derives the degree and angle of linear polarization analytically.
| File | Purpose | Required for final inference |
|---|---|---|
genpolar_one_step.pth | Distilled one-step UNet and ControlNet | Yes |
genpolar_vae_encoder_lora/ | VAE encoder LoRA adapter used by the one-step model | Yes |
genpolar_stage1_teacher.pth | Stage-one diffusion teacher used for distillation and stage-one reproduction | No |
The .pth files are inference-focused exports. They contain only unet_state_dict and controlnet_state_dict, plus small format metadata. Optimizer states, training counters, the fake score model, training arguments, and duplicate state dictionaries are intentionally excluded.
All released tensors retain their original FP32 values.
The code initializes model components from runwayml/stable-diffusion-v1-5 before loading the GenPolar state dictionaries.
Place the downloaded files under release_weights/, then run:
python inference.py \
--ckpt_path ./release_weights/genpolar_one_step.pth \
--vae_lora_dir ./release_weights/genpolar_vae_encoder_lora \
--input_folder ./data/DfP \
--results_folder ./results \
--fp16
The input directory format and full environment setup are documented in the GenPolar source repository.
SHA-256 hashes are provided in SHA256SUMS.