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

  • Image generation — text-to-image with Z-Image and FLUX.2 Klein (4B/9B) model families, plus Ideogram 4 (FP8) on macOS/MLX
  • Video generation — text-to-video and image-to-video with platform-specific LTX aliases across macOS, Windows, and Linux
  • Cross-platform — automatic backend selection: MLX on macOS, diffusers/CUDA on Windows and Linux for images, and the shared diffusers/CUDA LTX backend on Windows and Linux for video
  • Prompt system — YAML prompt files with variables, structured prompts, snippets, and batch runs
  • Model store — central ~/.ziv/ directory with bare-name resolution and HuggingFace fallback
  • LoRA support — single or stacked, configurable weights, bare-name resolution
  • Image upscale — generate small → Lanczos → img2img refine → CAS sharpen
  • Video upscale — 2× spatial upscaling through the platform LTX backend when supported by the selected runtime
  • Reference images — img2img steering from any starting image
  • Model variants — image quantization across supported image backends, plus macOS MLX video Q4/Q8 aliases
  • Post-processing — contrast, saturation, and CAS sharpening (image only)
  • Interactive controls — skip, quit, pause, and repeat during batch runs (image only)

Platform Support

Platform Image Generation Video Generation
macOS (Apple Silicon) ✅ Z-Image / FLUX / Ideogram 4 via mflux/MLX ✅ LTX via MLX aliases (ltx-4, ltx-8)
Windows (NVIDIA GPU) ✅ Z-Image / FLUX via diffusers/CUDA ✅ LTX via diffusers/CUDA alias (ltx-2.3)
Linux (NVIDIA GPU) ✅ Z-Image / FLUX via diffusers/CUDA ✅ LTX via diffusers/CUDA alias (ltx-2.3)

Installation

Requires Python 3.14+ and uv.

uv is required. This package cannot be installed with pip — some dependencies require uv-specific resolution that pip does not support. All commands below use uv.

# Install globally from PyPI
uv tool install z-vision-generator

# Install globally from repository
uv tool install -e git+https://github.com/knuthelge/ZVisionGenerator.git

# Development setup
git clone https://github.com/knuthelge/ZVisionGenerator && cd ZVisionGenerator
uv sync

Video generation requires ffmpeg. On Windows and Linux, image and video generation require an NVIDIA GPU with CUDA available to PyTorch.

The packaged Windows/Linux ltx-2.3 alias defaults to the configurable diffusers-converted repository dg845/LTX-2.3-Diffusers. This is the diffusers-compatible layout required by the Windows/Linux video backend, not an official Lightricks alias. Override it in ~/.ziv/config.yaml if you want to point ltx-2.3 at a different compatible diffusers repository.

The macOS video aliases ltx-4 and ltx-8 are the shipped MLX Q4/Q8 presets. Windows and Linux use the diffusers-backed ltx-2.3 alias instead, so the Q4/Q8 naming does not carry across platforms.

Quick Start

# Generate an image (bare name from ~/.ziv/models/)
ziv-image -m my-model --prompt "a beautiful sunset"

# Generate from a HuggingFace model
ziv-image -m Tongyi-MAI/Z-Image-Turbo --prompt "a cat in a garden"

# Batch run from a prompts file
ziv-image -m my-model -p prompts.yaml -r 3

# Generate a video on macOS
ziv-video -m ltx-4 --prompt "A cat walking through a garden"

# Generate a video on Windows or Linux
ziv-video -m ltx-2.3 --prompt "A cat walking through a garden"

# Image-to-video on macOS
ziv-video -m ltx-4 --image photo.jpg --prompt "Camera zooms in slowly"

# Image-to-video on Windows or Linux
ziv-video -m ltx-2.3 --image photo.jpg --prompt "Camera zooms in slowly"

# Launch the Web UI
ziv ui

# Show command help and available subcommands
ziv

The Web UI is an explicit local launcher: use ziv ui or ziv-ui. Running bare ziv prints command-discovery help without starting a browser or server. If a local environment is missing required Web UI packages, the launcher reports how to repair the base install instead of failing with an import traceback.

The packaged Web UI is served from local static files and does not fetch cloud fonts or other font assets at runtime. It uses local system font fallbacks when Inter or JetBrains Mono are not installed.

Tip: ziv image, ziv video, and ziv model are also available as subcommands of the unified ziv parent command. Use ziv -h or ziv --help to print terminal help.

Documentation

Full documentation is available at knuthelge.github.io/ZVisionGenerator.

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

License

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

Metadata

Release files for z-vision-generator 0.13.0b3

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 0.13.0b3
File Size Uploaded Provenance Actions
z_vision_generator-0.13.0b3.tar.gz 987.0 kB With provenance Details for z_vision_generator-0.13.0b3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for z-vision-generator 0.13.0b3
File Interpreter ABI Platform Actions
z_vision_generator-0.13.0b3-py3-none-any.whl Python 3 none any Details for z_vision_generator-0.13.0b3-py3-none-any.whl

Total release size: 1.5 MB

Release files / z_vision_generator-0.13.0b3.tar.gz

Download URL z_vision_generator-0.13.0b3.tar.gz
Size 987.0 kB
Tags Source
SHA-256 checksum
How to use checksums
d5401845bb103eea95e65317b20d922162989dd012c86884eb13b817386da1c4
BLAKE2b-256 checksum
How to use checksums
0d57ccbf8d8fa41f436b5abd741f400cf0edc790cd188409bd57c1597246885d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 3, 2026.

Transparency log

Release files / z_vision_generator-0.13.0b3-py3-none-any.whl

Download URL z_vision_generator-0.13.0b3-py3-none-any.whl
Size 475.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
47bcfffff4e0488684b36d3ba02db8e22eedd1696e2dcd1dd0e6d2c6b4ecab15
BLAKE2b-256 checksum
How to use checksums
a2c85da2a75b4cfd207e2fc4a7e7c66ef74afc6dc7e4661fe96ba89b308ba8f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 3, 2026.

Transparency log

Security for z-vision-generator 0.13.0b3

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-0.13.0b3.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 3, 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