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 MOSS-Image.
- Prompt guidance works: the simplest
transform to realismor转成写实照片takes effect. Adding words like "candid snapshot, HD photo, strongly contrasted sunlight" also works, and within a range you can steer character age, clothing color and material, etc. via prompts. - MOSS recognizes some content very well, but it can also be very sensitive to prompts, which may reduce consistency.
- The workflow can be taken directly from the sample images. Note that sampling parameters — sampler, scheduler, even denoise (it doesn't have to be 1), and latent size — all influence the result. Try different settings.
中文 —基于 MOSS-Image 训练的转写实编辑 LoRA。
- 提示词引导会发挥作用：最简单的 "transform to realism" 或 "转成写实照片" 就会生效；也可以加上「随手拍、高清照片、强烈对比的阳光」等提示词，甚至在一定程度上通过提示词调整角色年龄、服装颜色材质等。
- MOSS 对部分内容有很好的识别能力，但对提示词也可能非常敏感，会导致一致性下降。
- 工作流可以在样图里直接取得。请注意：不同的采样参数——包括采样器、调度器甚至降噪率（不必定要是 1），还有 latent 尺寸——都会对结果产生影响，请多尝试。
FAQ
Comments (5)
I like this, can you make a version for anima checkpoint?
Hi,
where can i find the workflow? thank you
Realism Transform for Moss is genuinely insane brother, holy!
"Every preview image embeds its ComfyUI workflow — drop one onto the canvas to load it."
Maybe I missed something but does this really work? I just downloaded a pic and tried to load it on ComfyUI, but I get only the pic that loads.
The bottom right corner of the pic has a "!" icon, click on it and you will see comfy nodes,clip copy and press control+v on your comfyui page