Anime / illustration → photorealistic transform
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.
- Prompt guidance is effective across versions: the simplest
transform to realism/转成写实照片works, and extra prompt words can steer lighting, mood, clothing color and material — even character age — within a range. - Every preview image embeds its ComfyUI workflow — drop one onto the canvas to load it.
- Sampling settings matter: sampler, scheduler, denoise (it does not have to be 1) and latent size all influence the result. Experiment freely.
Non-commercial use only. Re-uploads and ad-farm mirrors are not tolerated.
动漫 / 插画 → 写实照片转换
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。
- 各版本对提示词引导均有响应：最简单的
transform to realism/转成写实照片即可生效；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。 - 每张预览图都内嵌完整 ComfyUI 工作流，拖入画布即可加载。
- 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。
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。
Description
EN — Realism-transform edit LoRA trained on Krea 2.
- Prompt-responsive:
transform to realismworks on its own; adding prompt words can shift lighting, background and more to a degree. - Stacks well with other style LoRAs and face LoRAs.
- 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!
- 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!
中文 —基于 Krea 2 训练的转写实编辑 LoRA。
- 对提示词有响应：直接用
transform to realism即可；添加提示词可在一定程度上修改光影、背景等。 - 可以配合其他风格 LoRA 和人脸 LoRA 使用。
- 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！
- 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。
FAQ
Comments (3)
好東西,謝謝大佬了