Pid Flux2
nvidia-license
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 2,54–2,61 GB
- Versión
- v2k
- Actualizado
- 9 oct 2026
- Fuente
- Hugging Face
Descripción de la fuente
PiD — flux2 2kto4k decoder (SceneWorks redistribution)
A format-converted redistribution of NVIDIA's PiD (Pixel Diffusion) 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).
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
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).
⚠️ 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_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. |
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.
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_flux2_distill_4step/model_ema_bf16.pth - v1.0
2kto4k:checkpoints/PiD_res2kto4k_sr4x_official_flux2_distill_4step_2606/model_ema_bf16.pth - v1.0
res2k:checkpoints/PiD_res2k_sr4x_official_flux2_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
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 9 oct
Artefactos del modelo
3 artefactos
Artefactos del modelo
3 artefactosExtractos de fuentes
2 extractos
Extractos de fuentes
2 extractos--- license: other license_name: nvidia-license license_link: LICENSE tags: - pixel-diffusion - decoder - super-resolution - non-commercial - sceneworks extra_gated_prompt: >- This model is licensed under the NVIDIA License (NSCLv1). It and any derivative works may be used for NON-COMMERCIAL (research or evaluation) purposes only. The non-commercial restriction flows to decoded output. --- # PiD — flux2 2kto4k decoder (SceneWorks redistribution) A format-converted redistribution of NVIDIA's **PiD** (Pixel Diffusion) `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). 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 `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). ## ⚠️ License — non-commercial (research/evaluation) only This checkpoint is under the **NVIDIA License** (HuggingFace tag `NSCLv1`); see [`LICENSE`](LICENSE) and [`NOTICE`](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_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). | | `NOTI...
Source context: 0 downloads · 0 likes · Repo SceneWorks/pid-flux2
