Hassakuxlillustrious V22

🚀 Quick Start

You can run Hassaku XL and use its API on SinkIn: SinkIn Link

✨ Features

• Anime Style: Hassaku is designed to generate anime - style images with a bright and distinct look.
• Quality Training: V1 uses illustrious - xl as the base. Versions from 0.2M up are trained with quality prompts like "masterpiece" or "worst quality".
• Multiple Variants: There is also a pony xl variant available.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

You can use the following prompts to generate images:

1girl, masterpiece, twin braids, solo, looking at viewer, blue eyes, long hair, pink hair, smug, pink pupils, tongue, nun, outdoors, veil, cross necklace,

With negative prompt:

worst quality, bad quality, 

Advanced Usage

You can experiment with different prompts and negative prompts to get various results. For example, using different character descriptions, settings, and moods in the prompts.

📚 Documentation

Model Details

Using the Model

⚠️ Important Note

The model is trained with images having minimal disruptive features like floating texts, logos, speak bubbles, and signatures. If such features appear in an image, use the prompt "signature" as a negative prompt. Exclude metadata and franchise tags; don't use them. For example, metadata like "highres" and franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".

💡 Usage Tip

Recommended negative prompts are "worst quality, bad quality", and positive prompts can include "masterpiece".

Good Resolution Options for SDXL

• 1024 x 1024
• 1152 x 896
• 896 x 1152
• 1216 x 832
• 832 x 1216 (most recommended)
• 1344 x 768
• 768 x 1344
• 1536 x 640
• 640 x 1536

🔧 Technical Details

The model V1 uses illustrious - xl as the base. Versions from 0.2M up are trained with quality - related prompts.

📄 License

Because it merges ANIMAGINE XL 3.0 below version V1 and Illustrious - XL & WAI - NSFW - illustrious - SDXL beginning from V1, it uses the Fair AI Public License 1.0 - SD. V2 is trained on its own, only using Illustrious - XL 0.1, and also uses the Fair AI Public License 1.0 - SD license.

Source

Model Source

Credit

Credit

Trigger words

You should use None to trigger the image generation.

Download model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

Support

My Discord is for everything related to anime models and art. You can support me on my patreon. My models include hassaku, sudachi(flat 2d), koji(2d), yuzu(light semirealistic). Thanks to my supporters Riyu, SETI, and Kodokuna on my patreon!