# nv-tlabs/PiD

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Repository: https://github.com/nv-tlabs/PiD
Canonical: https://ross.abutalabs.com/products/pid
Homepage: https://research.nvidia.com/labs/sil/projects/pid/
Language: Python
License: NOASSERTION
License Family: other
Topics: diffusion-decoder, pixel-diffusion
Last push: 2026-07-22T02:08:59+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 7
- inputs: {"age_days": 105, "days_push": 43, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1045, forks 61 (observed 2026-08-28T04:03:21.572800+00:00)

## What it is
PiD is a plug-and-play pixel diffusion decoder from NVIDIA that replaces VAE/RAE decoders, decoding latent representations directly into high-resolution pixels in a single pass. It unifies decoding and upsampling (4x-8x) into one generative module and supports latents from FLUX, SD3, SDXL, Qwen-Image, DINOv2, and SigLIP.

## Use cases
- decode latent diffusion model outputs to high-resolution images
- upscale 512x512 latents to 2048x2048 pixels quickly
- replace VAE decoder in text-to-image pipelines
- decode DINOv2 or SigLIP semantic latents into images
- integrate high-resolution decoding into ComfyUI workflows
- early-exit latent diffusion by decoding partially denoised latents

## When to choose
- you need fast, high-resolution image decoding from latent diffusion models
- you want to replace the decode-then-super-resolve cascade with lower latency
- you work with FLUX, SD3, SDXL, or Qwen-Image latents and need 4K output
- you need a distilled few-step decoder for consumer GPUs

## When to avoid
- you need a lightweight deterministic decoder without diffusion sampling
- your environment lacks a CUDA-capable GPU with sufficient VRAM
- you need non-image modalities or non-PyTorch frameworks

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, machine-learning, artificial-intelligence
- platform: python, windows
- tags: diffusion-decoder, pixel-diffusion, super-resolution, latent-decoding, text-to-image, nvidia, comfyui, gpu, linux, macos

## Member repositories
- nv-tlabs/PiD (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.572800+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:07.001244+00:00, confidence not recorded.
  - readme: https://github.com/nv-tlabs/PiD (fetched 2026-08-28T04:03:21.572800+00:00, sha 1377e36bf2f9)
  - homepage: https://research.nvidia.com/labs/sil/projects/pid/ (fetched 2026-08-29T13:03:20.733361+00:00, sha 9e10b57503c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.