🚀 Evt_V3
Evt_V3 基于 Evt_V2 模型,使用 35467 张图像进行了 20 个轮次的微调训练。该模型可用于文本到图像的转换,尤其擅长生成动漫风格的图像。
✨ 主要特性
- 基于稳定扩散(Stable Diffusion)技术,能够生成高质量的动漫风格图像。
- 在 Evt_V2 的基础上进行微调,进一步提升了图像生成的质量和效果。
💻 使用示例
基础用法
以下是一些使用该模型生成图像的示例,包含正向提示词、负向提示词、步数、采样器、CFG 缩放比例和 Clip 跳过参数等信息。
示例 1

正向提示词:best quality, illustration,highly detailed,1girl,upper body,beautiful detailed eyes, medium_breasts, long hair,grey hair, grey eyes, curly hair, bangs,empty eyes,expressionless, ((masterpiece)),twintails,beautiful detailed sky, beautiful detailed water, cinematic lighting, dramatic angle,((back to the viewer)),(an extremely delicate and beautiful),school uniform,black ribbon,light smile
负向提示词:lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,artist name,bad feet
步数:40
采样器:Euler a
CFG 缩放比例:6
Clip 跳过:2
示例 2

正向提示词:masterpiece, best quality, {best quality}, {{masterpiece}}, {highres}, original, extremely detailed wallpaper, 1girl,{an extremely delicate and beautiful}, {{angle}} , hair flower, illustration, school uniform, sunlight, detailed eyes, lily, white wings, ((halo)), silver hair
负向提示词:lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark, username, blurry, artist name,bad feet
步数:40
采样器:Euler a
CFG 缩放比例:6
Clip 跳过:2
示例 3

正向提示词:{{best quality}}, {{masterpiece}}, {{ultra-detailed}}, {illustration}, {detailed light}, {an extremely delicate and beautiful}, a girl, {beautiful detailed eyes}, stars in the eyes, messy floating hair, colored inner hair, Starry sky adorns hair, depth of field
负向提示词:lowres, bad anatomy, text, error, extra digit, fewer digits, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, {blurry:1.1}, missing arms
步数:40
采样器:Euler a
CFG 缩放比例:7
Clip 跳过:2
📄 许可证
本模型使用的许可证为 creativeml-openrail-m
。