Views
No views yet
flux2
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).flux2 student serves the FLUX.2 VAE latent space (the packed 128-channel latent)
— FLUX.2-dev, the FLUX.2-klein-9b variants, Lens (base/turbo), and Ideogram 4
(base/turbo).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).| File | Description |
|---|---|
pid_flux2_2kto4k_v1pt5.safetensors | PiD v1.5 flux2 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, and it retires the v1.0 _2606 color-drift workaround — v1.5 fixes color fidelity at the source. |
pid_flux2_2kto4k.safetensors | flux2 v1.0 2kto4k 4-step student (456 tensors, bf16, ~2.7 GB). Retained as the fallback for installs that predate v1.5. |
pid_flux2_2k.safetensors | flux2 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. |
2kto4k file loads correctly, and an install with only the v1.0 file keeps working.nvidia/PiD)
via a lossless key/format transform (net.-prefix strip + drop training-only
net_ema.*/fake_score.*/discriminator.*; dtype preserved). No re-training.2kto4k: checkpoints/PiD_v1pt5_res2kto4k_sr4x_official_flux2_distill_4step/model_ema_bf16.pth2kto4k: checkpoints/PiD_res2kto4k_sr4x_official_flux2_distill_4step_2606/model_ema_bf16.pthres2k: checkpoints/PiD_res2k_sr4x_official_flux2_distill_4step/model_ema_bf16.pth