Qwen-Zhongkui-钟馗

LORA
Original


Updated:

This is a character Lora, a mythological figure from China. However, it can also be used as a style Lora that enhances Chinese and dark elements, including: thick painting, oil painting, ink painting, 3D rendering, realism, and other styles.

这是一个人物Lora,是中国的一个神话人物。但是也可以当成强化中国元素和黑暗元素的风格Lora来使用,包括了:厚涂,油画,水墨画,3D渲染,写实,等风格。

0.3-0.8,

Conventional: 30 steps, cfg4-6, Euler.

Recommended: Qwen-Image Lightning Lora: 8-10 steps, cfg1, DPM++2M_SDE Karras,

For resolution, refer to the recommended size for qwen-image. A smaller size will affect text clarity. I usually use 9:16, 928x1664.

分辨率请参考qwen-image推荐尺寸。尺寸太小会影响文字清晰度。我常用的是9:16,928X1664。

I used segmented natural language annotation, with manual bilingual annotation in Chinese and English. This should facilitate Chinese recognition and understanding.

我使用了分段式自然语言标注,中英文双语手动打标。这应该更有助于识别和理解中文。

I made Lora for the Tensor x Qwen event. Um... so please give me a prize.😻😻😻

这是为 Tensor x Qwen 活动做的 Lora。嗯……所以请给我一份奖品。😻😻😻

Version Detail

Trained by Tensor
Qwen-Image
11
Conventional: 30 steps, cfg4-6, Euler. Using Qwen-Image Lightning Lora: 8-10 steps, cfg1, DPM++2M_SDE Karras, 0.3-0.8

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts