Clandestine Xl 1.0

🚀 Clandestine XL 1.0

Clandestine XL 1.0 is a fine - tuned model based on Kivotos XL 2.0, specializing in generating sharp - lined anime illustrations. It takes inspiration from popular AI - generated art styles on Pixiv, and can produce high - quality stylized anime characters with improved anatomy and hand renderings.

🚀 Quick Start

Using the Model on Our Platform

You can use this model on our platform by clicking the following button:

Using in Other Tools

You can also use it in ComfyUI or Stable Diffusion Webui, or with 🧨 diffusers.

✨ Features

• Stylized Anime Generation: Specializes in generating sharp - lined anime illustrations inspired by popular AI - generated art styles on Pixiv.
• Improved Anatomy and Hand Renderings: Can produce stylized anime characters with better anatomical details and hand renderings.
• Inherited Special Tags: Inherits special tags from Animagine XL 3.1 to enhance image generation in terms of quality, rating, creation date, and aesthetic.

📦 Installation

First, install the required libraries:

pip install diffusers transformers accelerate safetensors --upgrade

💻 Usage Examples

Basic Usage

import torch
from diffusers import StableDiffusionXLPipeline

pipe = StableDiffusionXLPipeline.from_pretrained(
    "yodayo-ai/clandestine-xl-1.0", 
    torch_dtype=torch.float16, 
    use_safetensors=True,
    custom_pipeline="lpw_stable_diffusion_xl",
    add_watermarker=False,
    variant="fp16"
)
pipe.to('cuda')

prompt = "1girl, kazusa \(blue archive\), blue archive, solo, upper body, v, smile, looking at viewer, outdoors, night, masterpiece, best quality, very aesthetic, absurdres"
negative_prompt = "nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn"

image = pipe(
    prompt, 
    negative_prompt=negative_prompt,
    width=832,
    height=1216, 
    guidance_scale=7,
    num_inference_steps=28
).images[0]

image.save("./cat.png")

📚 Documentation

Tag Ordering

For optimal results, follow the structured prompt template:

1girl/1boy, character name, from which series, by which artists, everything else in any order.

Special Tags

Clandestine XL 1.0 inherits special tags from Animagine XL 3.1:

• Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
• Rating tags: safe, sensitive, nsfw, explicit
• Year tags: newest, recent, mid, early, oldest
• Aesthetic tags: very aesthetic, aesthetic, displeasing, very displeasing

Recommended Settings

• Negative prompts:

nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn

• Positive prompts:

masterpiece, best quality, very aesthetic, absurdres

• Classifier - Free Guidance (CFG) Scale: around 5 to 7; 10 is fried, >12 is deep - fried.
• Sampling steps: around 25 to 30; 28 is the sweet spot.
• Sampler: Euler Ancestral (Euler a) is highly recommended.
• Supported resolutions:

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

📄 License

Clandestine XL 1.0 is under the Fair AI Public License 1.0 - SD license, which is compatible with Stable Diffusion models’ license. Key points:

1. Modification Sharing: If you modify Clandestine XL 1.0, you must share both your changes and the original license.
2. Source Code Accessibility: If your modified version is network - accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
3. Distribution Terms: Any distribution must be under this license or another with similar rules.

🔧 Technical Details

Model Details

Gallery

Clandestine XL 1.0