Mindket

safetensored-upscalers

Newversion 1 · updated

Overview

Image upscaling models, and a few other image-to-image ones, gathered in one repository as safetensors files converted from older pickle files. For people who run upscalers on their own computer.

safetensored-upscalers is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python on Windows, macOS or Linux
  • Enough disk space for the model files you fetch
Runs in
  • Windows, macOS or Linux with Python, to download the files
  • Your own image tool or script that can load safetensors weights
  • The Hugging Face page, to read MODELS.md before choosing a model
Start with
pip install -U huggingface_hub
hf download AshtakaOOf/safetensored-upscalers

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

This repository gathers image upscaling models, plus a few other image-to-image ones, and stores them as safetensors files. They began as older pickle files and were converted. The uploader says they own none of the models, and a MODELS.md file in the repository explains what each one is for.

Who it suits

It suits anyone who runs image upscalers on their own machine and prefers safetensors files over pickle ones. It also helps people who want many upscalers in one place instead of hunting for each.

IndustryWho uses itHow they use itExample
PhotographyPhoto editorsEnlarge low-resolution pictures with a chosen upscalerScaling up a small old photo
Game moddingModdersUpscale old textures before using them againSharpening a low-resolution texture
AI hobby workModel tinkerersTry several upscalers on one picture and compare themTesting two models on the same image
DesignDesignersEnlarge artwork or a still imagePreparing a small image at a larger size

If you want a finished app, or a model with ready run steps, you can skip it, since the card gives none.

Where to use it

You download the files on Windows, macOS or Linux, then load them in your own tools.

  • Windows, macOS or Linux with Python, to download the files
  • Your own image tool or script that can load safetensors weights
  • The Hugging Face page, to read MODELS.md before choosing a model
Use caseWhoWhat they get back
Upscaling picturesPhoto editorsA larger version of a low-resolution image
Picking a modelNewcomersNotes in MODELS.md on what each model does
Swapping file formatPeople who avoid pickle filesThe same kinds of models as safetensors files

How to set it up

You need Python and the Hugging Face hub package, which the download command uses.

  • Python on Windows, macOS or Linux
  • Enough disk space for the model files you fetch
  1. Install the Hugging Face hub package.
  2. Download the repository to your computer.
  3. Open MODELS.md and pick the model that fits your job.
pip install -U huggingface_hub
hf download AshtakaOOf/safetensored-upscalers

How to use it

The card gives no run steps of its own. You fetch the files with the command above, read MODELS.md, then load the file you chose in a tool that reads safetensors.

hf download AshtakaOOf/safetensored-upscalers

Example

You run hf download AshtakaOOf/safetensored-upscalers. The repository's files land on your computer, and MODELS.md tells you which upscaler to try first on a small photo.

For newcomers and experts

An upscaler is a model that makes a picture larger and fills in detail. Start small. Download the repository, open MODELS.md, and read about one model before loading anything.

If you know the field, the point is the file format. The uploader converted pickle weights using a modified version of a conversion script from OpenModelDB, edited with Gemini 2.5 Pro. The conversion is only as good as that script, and nothing here is newly trained.

  1. Original upscaler files in pickle form
  2. Conversion script turns them into safetensors
  3. Files are stored in one repository
  4. You download the repository
  5. You load a file in your own tool

Good to know

The files are copies of other people's models, so the uploader is not their author.

  • License: MIT, as Hugging Face lists it
  • Cost to run: none named
  • Data it reaches: only the files you download, with no account, clipboard or web service named
  • Not for: claiming the models as original work, since the uploader says they own none of them

README and files

README

safetensored-upscalers

Image upscaling models, and a few other image-to-image ones, gathered in one repository as safetensors files converted from older pickle files. For people who run upscalers on their own computer.

Made by AshtakaOOf on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository gathers image upscaling models, plus a few other image-to-image ones, and stores them as safetensors files. They began as older pickle files and were converted. The uploader says they own none of the models, and a MODELS.md file in the repository explains what each one is for.

Who it suits: It suits anyone who runs image upscalers on their own machine and prefers safetensors files over pickle ones. It also helps people who want many upscalers in one place instead of hunting for each.

Industry | Who uses it | How they use it | Example
Photography | Photo editors | Enlarge low-resolution pictures with a chosen upscaler | Scaling up a small old photo
Game modding | Modders | Upscale old textures before using them again | Sharpening a low-resolution texture
AI hobby work | Model tinkerers | Try several upscalers on one picture and compare them | Testing two models on the same image
Design | Designers | Enlarge artwork or a still image | Preparing a small image at a larger size

If you want a finished app, or a model with ready run steps, you can skip it, since the card gives none.

Where to use it: You download the files on Windows, macOS or Linux, then load them in your own tools.

  • Windows, macOS or Linux with Python, to download the files
  • Your own image tool or script that can load safetensors weights
  • The Hugging Face page, to read MODELS.md before choosing a model
Use case | Who | What they get back
Upscaling pictures | Photo editors | A larger version of a low-resolution image
Picking a model | Newcomers | Notes in MODELS.md on what each model does
Swapping file format | People who avoid pickle files | The same kinds of models as safetensors files

How to set it up: You need Python and the Hugging Face hub package, which the download command uses.

  • Python on Windows, macOS or Linux
  • Enough disk space for the model files you fetch
  1. Install the Hugging Face hub package.
  2. Download the repository to your computer.
  3. Open MODELS.md and pick the model that fits your job.
pip install -U huggingface_hub
hf download AshtakaOOf/safetensored-upscalers

How to use it: The card gives no run steps of its own. You fetch the files with the command above, read MODELS.md, then load the file you chose in a tool that reads safetensors.

hf download AshtakaOOf/safetensored-upscalers

Example: You run hf download AshtakaOOf/safetensored-upscalers. The repository's files land on your computer, and MODELS.md tells you which upscaler to try first on a small photo.

For newcomers and experts: An upscaler is a model that makes a picture larger and fills in detail. Start small. Download the repository, open MODELS.md, and read about one model before loading anything.

If you know the field, the point is the file format. The uploader converted pickle weights using a modified version of a conversion script from OpenModelDB, edited with Gemini 2.5 Pro. The conversion is only as good as that script, and nothing here is newly trained.

Original upscaler files in pickle form
Conversion script turns them into safetensors
Files are stored in one repository
You download the repository
You load a file in your own tool

Good to know: The files are copies of other people's models, so the uploader is not their author.

  • License: MIT, as Hugging Face lists it
  • Cost to run: none named
  • Data it reaches: only the files you download, with no account, clipboard or web service named
  • Not for: claiming the models as original work, since the uploader says they own none of them

On Hugging Face, 13 November 2026

  • Task: image to image
  • Formats: Safetensors
  • Downloads in the last 30 days: 44
  • Likes: 11
  • License: mit
  • Tags: image-enhancement, image-restoration, image-upscaling, safetensors, image-to-image

Links

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download AshtakaOOf/safetensored-upscalers

Then follow the usage in its model card. Nothing in this kit runs by itself.

Files
README.md  5 KB

1 file, 5 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-13

Compare with similar

Listed Hugging Face models in the same category that share the most tags with this one.

ProductDownloads, last 30 daysLikesParametersLicenseLast change
safetensored-upscalers This page4411—mit
Iris-3B by speridlabsShares image-restoration · safetensors9973503Bapache-2.0
FLUX.2 [klein] 4B BaseShares image-to-image · safetensors743,0551953.9Bapache-2.0
FLUX.2 [klein] 4BShares image-to-image · safetensors435,6431,1163.9Bapache-2.0
Qwen-Image-EditShares image-to-image · safetensors141,5202,58020.4Bapache-2.0
ControlNet v1.1 depth (SD 1.5)Shares image-to-image · safetensors22,04170361Mopenrail
Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New

Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…

New

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Similar in Developer

See all in Developer

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

buzz

block · Kit

Self-hostable workspace where people and AI agents share the same rooms, built on a Nostr relay that logs every action as a signed event. For teams that want t…

New37.3k

plannotator

backnotprop · Kit

Opens your AI coding agent's plans, specs and code changes in a browser so you can annotate or comment on them and send the feedback straight back to the agent.

New10.5k