My first LoRA! Trained on Chinese furry author: "Luhua 5S Pressed Golden Germ Corn Egg" (卤花5s压榨金胚玉米蛋 on Weibo)

Please support the real artists!

Based on Yiff in Hell model.

• Recommended CFG scale: 6–9

• Recommended steps: 40–44

• Trigger word: 5schinese (more to original style, add these: spiky hair, small horns, dynamic pose, powerful stance, painterly style, vibrant colors)

New v3 version is out!

Now you can choose two variants: Base and Extra
What's the difference?

• Base — trained on 30 images, anime-ish style, less vibrant colors, and a more grounded, natural look. - This is the most versatile option, and personally my favorite;

• Extra — trained on 57 images, more colorful, finer details, and different way of tagging - A bit blueish, and may struggle with certain angles due to training dataset to the original author's style.

Pick Base version if you are unsure, it's more stable and works well.

v2 version is out!

• More references,

• More training epochs,

• More detailed faces and anatomy compared to v1

Please take note negative prompt without these and similar keywords: bad quality, worst quality, low quality, worst detail, boring angle, bad angle, very displeasing — greatly influences the final generation results.

Resolution limitations

This LoRA was trained on images with a native resolution of approximately 1024px on the shorter side, primarily using a 2:3 aspect ratio. For best results, use a similar aspect ratio and resolution as from the examples from OP.

Generating at resolutions below 1024px may result in:

• Blurriness and loss of fine details,

• Distorted anatomy and structural issues,

• Increased noise, artifacts, and overall degradation of image quality

Recommendations:

• For best results, generate at 1024x1536 or higher (e.g., 1024x1920 (2:3) or 1920x1080 (3:2)), this matches the training resolution and aspect ratio of the used training dataset, delivering the best detail and stability.

The default CivitAI generator and its built‑in workflow that using suboptimal settings (resolution handling) that hurt quality. It's better to use ComfyUI with the workflow provided below – it's based and fine‑tuned for this and other LoRA's.

Example workflow used in ComfyUI:

Be sure to check out the Suggested Resources tab too. Any tips, reviews, or feedback for future training would be appreciated!