Update to NVIDIA's fast open-source upscaler with better detail and color fidelity than v1. Works with latent images, Flux and Z-Image, turning 512x512 into 2K in seconds on a consumer GPU.
PiD v1.5
by NVIDIA
NVIDIA's open-source image upscaler, v1.5, for latent, Flux and Z-Image outputs, targeting fast 2K results on consumer GPUs.
Updated EU status checked Last shown
PiD v1.5 at a glance
- What is PiD v1.5?
- PiD v1.5 is a model from NVIDIA. NVIDIA's open-source image upscaler, v1.5, for latent, Flux and Z-Image outputs, targeting fast 2K results on consumer GPUs.
- Who makes PiD v1.5?
- PiD v1.5 is made by NVIDIA.
- Does PiD v1.5 work in the EU?
- Unverified. No explicit evidence found. It is described as open source and runnable locally, but the license terms were not verified. Last verified 14 Nov 2026.
- How much does PiD v1.5 cost?
- Open source. Described as open source; no pricing information found. Runs locally on consumer GPUs.
- Where was PiD v1.5 shown?
- In 1 creator video by AI Search. Most recently by AI Search on 19 Jul 2026, at 4:21 in “Kimi K3, dancing waifus, robot UFC, song to MIDI, GPT Red, hoverboards: AI NEWS”.
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
PiD v1.5 is an update to NVIDIA's PiD image upscaler. According to a creator review, it improves detail and color fidelity over the first version and is described as fast and open source.
It is reported to work with latent images and with outputs from image generators such as Flux and Z-Image. In the creator's example it turns a 512x512 image into a 2K image within seconds on a consumer GPU.
No official page, repository or model card could be fetched, so the license, exact release date, architecture and hardware requirements are not confirmed here. Details should be verified against NVIDIA's official release.
- Upscales images, e.g. 512x512 to 2K, in seconds on a consumer GPU (creator report)
- Works with latent images and Flux / Z-Image outputs
- Improved detail and color fidelity over v1
- Described as open source by a creator
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
PiD
Model · Nvidia
NVIDIA pixel-diffusion decoder that turns latents into 2K–4K images, replacing VAE decode plus a separate upscaler.
Open-H3-Regenerate-2K
Model · NVIDIA
Open few-step diffusion refiner from NVIDIA that regenerates low-resolution H3 video drafts at 768P to 4K, 5–15 seconds.
Lucid Lyra
Model · Nvidia
NVIDIA research model that turns a single image into a queryable 3D Gaussian scene with semantics and object instances.
SeedVR2
Model · ByteDance
ByteDance's open-weights one-step diffusion transformer for restoring and upscaling video and images.
Sol Refiner
Model · Nvidia
NVIDIA one-step refiner that upscales low-resolution generated video to up to 4K across different base video generators.
RelayVSR
Model
Streaming real-world video super-resolution using sparse large-model keyframes and a lightweight propagation network.