Model reference · open weights

Fixer

Image nvidia Image edit 1 build Its own licence terms 512 dl/mo

Fixer is an open-weight image model from NVIDIA. Fixer (BF16) weighs 1.4 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • Fixer is a 0.6B parameter image-to-image diffusion model developed by NVIDIA to enhance and remove artifacts in rendered novel views for 3D reconstruction.
  • It operates in offline and online modes and is compatible with Neural Radiance Fields and 3D Gaussian Splatting representations.
  • The model uses a Linear Diffusion Transformer architecture based on Cosmos-Predict-0.6B, processes RGB images at a resolution of 576px by 1024px, and is governed by the NVIDIA Open Model License Agreement.

Summary of the nvidia/Fixer model card, 2026-10-01

What it is

Released byNVIDIA
Released2025-10-21
VRAM1.4 GB for the weights

What it runs on

Memory and cards for Fixer (BF16)

1.4 GBweights, file size
5.0 GBworking memory, one 1024² image
537 MBruntime overhead
CardOne imageMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. How to run this model is on its model card.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms