<h3>Anime / illustration → photorealistic transform</h3>
<p>Edit LoRAs that turn anime-style or illustrated images into realistic photographic style while following the input composition. One version per base model — currently MOSS-Image, Krea 2 and Qwen-Image 2.1; start from the newest.</p>
<ul>
<li>Prompt guidance is effective across versions: the simplest <code>transform to realism</code> / <code>转成写实照片</code> works, and extra prompt words can steer lighting, mood, clothing color and material — even character age — within a range.</li>
<li>Every preview image embeds its ComfyUI workflow — drop one onto the canvas to load it.</li>
<li>Sampling settings matter: sampler, scheduler, denoise (it does not have to be 1) and latent size all influence the result. Experiment freely.</li>
</ul>
<p>Non-commercial use only. Re-uploads and ad-farm mirrors are not tolerated.</p>
<hr />
<h3>动漫 / 插画 → 写实照片转换</h3>
<p>将二次元或插画图像转换为写实照片风格的编辑 LoRA，遵循输入构图。每个底模一个版本——目前有 MOSS-Image、Krea 2、Qwen-Image 2.1，建议从最新版本用起。</p>
<ul>
<li>各版本对提示词引导均有响应：最简单的 <code>transform to realism</code> / <code>转成写实照片</code> 即可生效；追加提示词可以在一定范围内调整光影氛围、服装颜色材质，甚至角色年龄。</li>
<li>每张预览图都内嵌完整 ComfyUI 工作流，拖入画布即可加载。</li>
<li>采样设置会影响结果：采样器、调度器、降噪率（不必是 1）、latent 尺寸都会带来变化，欢迎多尝试。</li>
</ul>
<p>本系列模型严禁商用（包括机翻打广告的搬运）。欢迎中文留言交流。</p>

Realism Transform

<p>EN — Realism-transform edit LoRA trained on Krea 2.</p>
<ul>
<li>Prompt-responsive: <code>transform to realism</code> works on its own; adding prompt words can shift lighting, background and more to a degree.</li>
<li>Stacks well with other style LoRAs and face LoRAs.</li>
<li>Thanks to its strong consistency control it also works for refining real-photo generations — yes, you can use it to upscale real photos, but faces will change!</li>
<li>This is a test build: an interesting dataset experiment, but not much time or compute went into testing. Some unusual art styles may fail to convert, and results vary with resolution and sampler changes. Have fun!</li>
</ul>
<p>中文 —基于 Krea 2 训练的转写实编辑 LoRA。</p>
<ul>
<li>对提示词有响应：直接用 <code>transform to realism</code> 即可；添加提示词可在一定程度上修改光影、背景等。</li>
<li>可以配合其他风格 LoRA 和人脸 LoRA 使用。</li>
<li>得益于一致性控制能力，也可以用它 refine 真人生成图——是的，可以拿来做真人照片的放大升频，但人脸会变！</li>
<li>这是一个测试版本：对数据集做了有趣的尝试，但没有太多时间和算力进行测试；某些特殊画风存在转换失败的可能；分辨率、采样器变化时画面都会有所变化。希望大家玩得愉快。</li>
</ul>

Files with SHA256: 8cbcfd3b744e70514e47773247d00a5270fc9d0d8e6c43aa8e49db3d97194f9a