SceneWorks/pid-flux

PiD — flux 2kto4k decoder (SceneWorks redistribution)

A format-converted redistribution of NVIDIA's PiD (Pixel Diffusion) flux 4-step distillation decoder, packaged for SceneWorks' native (no-PyTorch) PiD decoder (mlx-gen-pid on macOS/MLX, candle-gen-pid on Windows·Linux/CUDA).

PiD is an optional, per-generation replacement for the VAE decoder: it denoises directly in pixel space and decodes + 4× super-resolves in one 4-step pass. This flux student serves the FLUX.1-dev VAE latent space — FLUX.1 (dev/schnell), Boogu-Image (base/turbo/edit), Chroma (hd/base/flash), and Z-Image (turbo/edit), which share that VAE.

⚠️ License — non-commercial (research/evaluation) only

This checkpoint is under the NVIDIA License (HuggingFace tag NSCLv1); see LICENSE and NOTICE. Per §3.3, the Work and any derivative works may be used non-commercially — for research or evaluation purposes only (NVIDIA and its affiliates excepted).

This restriction flows to the output. Images decoded with PiD are for research/evaluation use only, distinct from the rest of the SceneWorks pipeline.

Contents

File	Description
pid_flux_2kto4k_v1pt5.safetensors	PiD v1.5 flux 2kto4k 4-step student (461 tensors, bf16, ~2.8 GB). Improved color fidelity, no grid-corner artifacts, better anime/face detail. The default for the 2kto4k (up-to-4K) output tier.
pid_flux_2kto4k.safetensors	flux v1.0 2kto4k 4-step student backbone + sigma-aware LQ adapter (456 tensors, bf16, ~2.7 GB). Retained as the fallback for installs that predate v1.5.
pid_flux_2k.safetensors	flux v1.0 res2k (2K-tuned) 4-step student. Sharper at 2048 px than the v1.5 2kto4k, so it serves the 2K output tier — NVIDIA ships no v1.5 res2k.
LICENSE	Full NVIDIA License text (verbatim from the original release).
NOTICE	NVIDIA attribution, provenance, and the exact conversion performed.

The engine picks v1.0 vs v1.5 by sniffing the weights (not the filename), so either 2kto4k file loads correctly, and an install with only the v1.0 file keeps working.

The PiD caption encoder (gemma-2-2b-it) and each model's VAE are provisioned separately by SceneWorks; this repo holds only the PiD student weights.

Provenance / conversion

Converted from NVIDIA's originals (from nvidia/PiD) via a lossless key/format transform (net.-prefix strip + drop training-only net_ema.*/fake_score.*/discriminator.*; dtype preserved). No re-training.

• v1.5 2kto4k: checkpoints/PiD_v1pt5_res2kto4k_sr4x_official_flux_distill_4step/model_ema_bf16.pth
• v1.0 2kto4k: checkpoints/PiD_res2kto4k_sr4x_official_flux_distill_4step/model_ema_bf16.pth
• v1.0 res2k: checkpoints/PiD_res2k_sr4x_official_flux_distill_4step/model_ema_bf16.pth

Links: Project https://research.nvidia.com/labs/sil/projects/pid/ · Code https://github.com/nv-tlabs/pid · Paper arXiv:2605.23902