Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

 

Z-Vision Generator logo with the Blob mascot

 

Z-Vision Generator

CI PyPI Python 3.14+ License: AGPL-3.0

Local AI image and video generation — hassle-free and fun. No tangled node graphs, no cloud dependencies, just prompts and results. Runs on macOS (Apple Silicon / MLX) and on Windows and Linux with NVIDIA CUDA through diffusers.

Features

  • Images from a prompt, with Z-Image, FLUX.2 Klein, Krea 2 Turbo, Ideogram 4 Instant and, on Windows and Linux, MOSS-Image.
  • Videos with sound from a prompt or a starting image, with LTX-2.3, LTX-2.5 and MiniMax H3. End on a chosen last frame with H3, and extend a clip to make it longer.
  • A prompt enhancer that runs on your machine and turns a short idea into a detailed prompt.
  • Upscaling of new and existing images, of video as it's made, and of existing videos on Windows and Linux.
  • Prompt files with random choices, reusable snippets and batch runs.
  • LoRAs, stacked and weighted, for images and video.
  • A Web UI for your computer, phone or tablet, and a CLI for scripts and batches, sharing the same models, prompt files and outputs.
Platform Images Video
macOS (Apple Silicon) ✅ via MLX ✅ via MLX
Windows (NVIDIA GPU) ✅ via diffusers/CUDA ✅ via diffusers/CUDA
Linux (NVIDIA GPU) ✅ via diffusers/CUDA ✅ via diffusers/CUDA

Install

Requires Python 3.14+, uv, and ffmpeg for video. On Windows and Linux: an RTX 20-series or newer NVIDIA GPU with driver 580 or newer.

uv tool install z-vision-generator
ziv ui

On Windows, add PyTorch's CUDA index to the install command; PyPI's PyTorch for Windows has no CUDA. See Install for the command and the details.

The Web UI opens in your browser and offers to download an image model picked for your machine.

Quick start

# Start the Web UI
ziv ui

# An image from the command line
ziv-image -m klein4b --prompt "A red fox sitting in fresh snow, early morning light"

# A batch from a prompt file, three runs each
ziv-image -m klein9b -p prompts.yaml -r 3

# A video with sound, and one from an image
ziv-video -m ltx-4 --prompt "A cat walking through a garden, birds singing"
ziv-video -m ltx-4 --image photo.jpg --prompt "The camera slowly zooms in"

Documentation

knuthelge.github.io/ZVisionGenerator

  • Web UI: your first image and video, and every page of the app
  • CLI: how-tos and the full command reference
  • Concepts: models, prompts, the enhancer, upscaling, memory and configuration
  • Developer: setting up, conventions and architecture

Contributing

Contributions are welcome. See CONTRIBUTING.md and the developer docs.

License

This project is licensed under the GNU Affero General Public License v3.0 or later.

Metadata

Release files for z-vision-generator 0.14.0b1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for z-vision-generator 0.14.0b1
File Size Uploaded Provenance Actions
z_vision_generator-0.14.0b1.tar.gz 6.5 MB With provenance Details for z_vision_generator-0.14.0b1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for z-vision-generator 0.14.0b1
File Interpreter ABI Platform Actions
z_vision_generator-0.14.0b1-py3-none-any.whl Python 3 none any Details for z_vision_generator-0.14.0b1-py3-none-any.whl

Total release size: 9.5 MB

Release files / z_vision_generator-0.14.0b1.tar.gz

Download URL z_vision_generator-0.14.0b1.tar.gz
Size 6.5 MB
Tags Source
SHA-256 checksum
How to use checksums
94ef145d25d92b1df10cb2289bc1327361a7ce2694e401ee7c76d32ff7f9692f
BLAKE2b-256 checksum
How to use checksums
48654850444e5e9489d0b0ac96b71c36f58658887ca691c43629316dae90fc80
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

Release files / z_vision_generator-0.14.0b1-py3-none-any.whl

Download URL z_vision_generator-0.14.0b1-py3-none-any.whl
Size 2.9 MB
Tags Python 3
SHA-256 checksum
How to use checksums
f98612b4f19aa3be7664271dd966242b9295e66d64463cca21f6e76688005452
BLAKE2b-256 checksum
How to use checksums
53ee3168b366b7f48dd3f7ea0c07b747e85c2512dc82e89ca31ee0be8fc163d9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

Security for z-vision-generator 0.14.0b1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for z_vision_generator-0.14.0b1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page