• https://tensor.art/u/596916453177820173/posts
• Here are some details for generating illustrations一些图例生成的信息在这里
• Official Version v1
Trigger word: xxmixgirl (It's better to include a trigger word, but it's not necessary.)
Negative: (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), tooth, open mouth, bad hand, bad fingers
Image size: 768*1280
Full body: It is recommended to enable HiRes and use Adobe Photoshop for facial retouching.
Portrait photo: HiRes is not necessary, facial retouching can be done using Adobe Photoshop.
Sampling iterations: 30
CFG Scale: 8-10
• buy me a coffee ☕
• 正式版v1
触发词:xxmixgirl-------没有触发词也可以,最好还是带上触发词。
反向提示词:(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), tooth, open mouth,bad hand,bad fingers,
图片尺寸:768*1280
全身:建议开hires,用ad修脸。
肖像照:可以不开hires,可以用ad修脸
采样次数:30
CFG Scale:8-10
• Test_v1
• Please read the text description carefully first
• Please pair with this Lora for better results
• At present, the characters have a strong sense of distortion, and the skin texture details are not clear enough. I hope to address these issues through continuous iterations.
• XXMix_9realisticSDXL is a fine-tuned model based on the Stable Diffusion XL model, aiming to improve the poor performance of Stable Diffusion XL in terms of the attractiveness of Asian female characters. The current v1 version is still in the experimental stage, with many issues, but I will continue to iterate and optimize.
• Trigger Words: xxmix girl woman (in some cases, it may be necessary to increase the weight of keywords)
• The known issues include:
• The character name or face style change may not work in some cases. In this situation, you can try to increase the weight of the trigger words.
• Since the model is trained based on a 10241024 canvas size, other image ratios may result in a higher error rate. It is recommended to use a 10241024 canvas size as much as possible, and I will try to train with dif