lilekitty / kaneko-gen

Generates unrestricted images from text prompts using a fine-tuned Stable Diffusion model

  • Public
  • 1.2K runs
  • License
Iterate in playground
Run with an API
Playground API Examples README Versions

Kaneko Gen

Kaneko Gen is a fine-tuned version of the Stable Diffusion model, modified to reduce censorship and safety filters. It enables unrestricted text-to-image generation and is intended for research, prompt testing, and creative experimentation.

Warning: This model may produce NSFW or sensitive content. Users must be 18 years or older.

Features

  • Based on Stable Diffusion (v1.4 or compatible)
  • Reduced or removed content filters
  • Supports custom prompts for open-ended image generation
  • Intended for research and experimentation only

How to Use

You can run this model on Replicate via the web interface or using Python code.

Python Example

import replicate

output = replicate.run(
    "lilekitty/kaneko-gen",
    input={
        "prompt": "a mysterious catgirl in a cyberpunk city, neon lights, ultra-detailed",
        "num_inference_steps": 30,
        "guidance_scale": 7.5
    }
)

print(output)  # This will be a URL to the generated image