怎么才能让FLUX生成的人物更像真人的照片

封面提示词：abstract network out of glass made of holographic liquid crystal,dark background,blue light reflections,symmetrical composition,centered in the frame,highly detailed,hyper-realistic,cinematic lighting,in the style of Octane Rende --ar 16:9 --style raw --personalize --v 6.1[💎查看更多风格和提示词](https://catjourney.life/)这周同样训练了一个FLUX Lora模型，褪色胶片风格，推荐权重0.6-0.8。非常适合生成毛茸茸的动物玩偶人像会偏向复古褪色的胶片风格涉及到玻璃制品产品展示摄影的表现很好整体景深模糊的也很好，过度自然柔和下载：https://www.liblib.art/modelinfo/4510bb8cd80142168dc42103d7c20f82?from=personal_page

官方说明和操作：DavidH：Hey @everyone @here we're testing a new"Character Reference"feature today This is similar to the"Style Reference"feature,except instead of matching a reference style it tries to make the character match a"Character Reference"image.How it worksType --cref URL after your prompt with a URL to an image of a characterYou can use --cw to modify reference 'strength' from 100 to 0strength 100(--cw 100)is default and uses the face,hair,and clothesAt strength 0(--cw 0)it'll just focus on face(good for changing outfits / hair etc)What it's meant forThis feature works best when using characters made from Midjourney images.It's not designed for real people / photos(and will likely distort them as regular image prompts do)Cref works similarly to regular image prompts except it 'focuses' on the character traitsThe precision of this technique is limited,it won't copy exact dimples / freckles / or tshirt logos.Cref works for both Niji and normal MJ models and also can be combined with --sref Advanced FeaturesYou can use more than one URL to blend the information /characters from multiple images like this --cref URL1 URL2(this is similar to multiple image or style prompts)How does it work on the web alpha?Drag or paste an image into the imagine bar,it now has three icons.selecting these sets whether it is an image prompt,a style reference,or a character reference.Shift+select an option to use an image for multiple categories Remember,while MJ V6 is in alpha this and other features may change suddenly,but V6 official beta is coming soon.We'd love everyone's thoughts in ⁠ideas-and-features We hope you enjoy this early release and hope it helps you play with building stories and worlds

XLabs-AI发布了6个不同Lora：mjv6_lora - Midjourney风格示例：A full-profile portrait of a Chinese dancer poised on a moonlit stone bridge,surrounded by the delicate blooms of a cherry orchard.Her silk garments ripple with her movement,her eyes are focused and intense,with skin details on her face.She's part of a scene inspired by classical poetry,her fluid motions a dance of elegance.The luminance is delicate and dreamlike,bestowing a soft ambiencerealism_lora -写实风格示例：In a conference room setting,a beauty women dressed in business attire are attending a meeting，random expressions,postures,and physical characteristicsa RAW ultra-realistic photo,UHD,8kanime_lora -动漫风格示例1girldisney_lora -迪斯尼风格示例：1cat,catoon,disney,scenery_lora -风景风格示例：A breathtaking view of the Himalayas mountain range,showcasing its majestic and serene beauty.The mountains are covered in snow,with their peaks reaching towards the sky,creating a stunning contrast with the blue horizon.The range is vast and imposing,with numerous towering peaks,including Mount Everest,the highest point on Earth.The scene captures the grandeur and tranquility of the Himalayas,with sunlight casting a soft glow on the snow-covered slopes.The foreground shows the rugged terrain and lush greenery of the lower elevations,adding to the diverse and spectacular landscape.art_lora -艺术风格Cat,European street,exploration,cozy,mysterious,colorful buildings,sunlight through leaves,cobblestone path,high definition,watercolor painting,warm tones,bright lighting effects,paper textureLora下载地址：https://hf-mirror.com/Kijai/flux-loras-comfyui/tree/main/xlabs