# nerdyrodent/VQGAN-CLIP

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Repository: https://github.com/nerdyrodent/VQGAN-CLIP
Canonical: https://ross.abutalabs.com/products/vqgan-clip
Language: Python
License: NOASSERTION
License Family: other
Topics: text2image, text-to-image
Last push: 2022-10-02T12:22:31+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1888, "days_push": 1431, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2647, forks 417 (observed 2026-08-28T04:07:06.803176+00:00)

## What it is
A Python application for running VQGAN+CLIP text-to-image generation locally on your own GPU, derived from Katherine Crowson's Google Colab notebook. It generates images from text prompts without needing cloud services like Colab.

## Use cases
- generate images from text prompts locally
- run VQGAN+CLIP without Google Colab
- create AI art on my own GPU
- text-to-image generation from the command line
- experiment with CLIP-guided image synthesis offline

## When to choose
- you have a CUDA-capable NVIDIA GPU with sufficient VRAM (8-24 GB)
- you want to generate VQGAN+CLIP images locally instead of via Colab
- you want a simple script-based text-to-image pipeline you can modify

## When to avoid
- you need modern high-quality text-to-image models like Stable Diffusion
- you lack a discrete GPU or have low VRAM
- you want a maintained project with active development or a clear license

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, cli
- domain: artificial-intelligence, image-processing, machine-learning, gpu-computing
- platform: python
- tags: vqgan, clip, text-to-image, generative-art, stable-diffusion-era, pytorch, local-generation, linux, gpu, docker

## Member repositories
- nerdyrodent/VQGAN-CLIP (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.803176+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:18:57.560542+00:00, confidence not recorded.
  - readme: https://github.com/nerdyrodent/VQGAN-CLIP (fetched 2026-08-28T04:07:06.803176+00:00, sha d3a30569d78b)
- Data as of 2026-08-30T08:39:29.467469+00:00.