RH Invite Code:
https://www.runninghub.ai/?inviteCode=rh-v1279
New user with 1000 free RH credit
All my workflow and models are avaible on RunningHub
F2K 9B Anything2Real A
New version of Anything2Real on F2K model.
Based on previous version, adjusted the style to more realistic and less 3D
Flux2 Klein 9B
Based on strong transformation ablitiy on Flux2 Klein 9B
The new anything2real lora adjusted aesthetic and image fidelity
Prompt:
transform the image into high quality realistic photograph. {male/female}
The model mostly trained on female images. Please add male if the input image is male.
Lora strength:
0.8-1
The lora tends to be a little bit more "3D" use less strength to gain more realistic from base model.
RH App One Click Transform Image:
https://www.runninghub.ai/ai-detail/2016070515554783233/?inviteCode=rh-v1279
RH Workflow:
https://www.runninghub.ai/post/2016060164108980226/?inviteCode=rh-v1279
RH Comparer with base:
https://www.runninghub.ai/ai-detail/2016075121722658818/?inviteCode=rh-v1279
RH Workflow:
https://www.runninghub.ai/post/2016072419668140033/?inviteCode=rh-v1279
Hugging Face:
https://huggingface.co/lrzjason/Anything2Real/tree/main
f2k_anything2real.safetensors
Qwen Edit 2511
RH APP:
https://www.runninghub.ai/ai-detail/2007507982543757313/?inviteCode=rh-v1279
RH online workflow:
https://www.runninghub.ai/post/2007432627858444289/?inviteCode=rh-v1279
Anything2Real 2601 A is an adjusted version which mixed alpha more and with extra weight adjustment based on 2601. It produces stronger transformation between image and realistic.
This LoRA, built on Qwen-Edit 2511, incrementally maps images of any visual style into the photographic domain. The training objective is to minimize perceptual distance rather than to perform pixel-level reconstruction.
Training Protocol
Dataset
7 style-paired subsets, 200 source images ≥ 1024 px, covering portraits, landscapes, and objects.
Training Pipeline
Two-stage tuning: (a) trigger-word + long-caption pairs, (b) trigger-word only.
Layer-wise merge with Anything2Real α; weights manually tuned to preserve low-frequency structure while replacing high-frequency texture.
Recommended Positive Prompt
transform the image to realistic photograph. {detailed description}
Note: {detailed description} is optional. Style-related tokens such as “anime”, “cyber”, or “oil-painting” are strictly forbidden; their inclusion will inject out-of-domain noise.
Strength Tuning
Default range: 0.8–1.0.
If over-smoothing or texture loss occurs, decrease in 0.1 steps down to 0.5.
Should realism remain insufficient, blend with an additional photorealistic LoRA and adjust to taste.
Because “realism” is inherently subjective, first modulate strength or switch base models rather than further increasing the LoRA weight.
Contact
Feel free to reach out via any of the following channels:
Twitter: @Lrzjason
Email: [email protected]
QQ Group: 866612947
WeChat ID:
fkdeaiCivitAI: xiaozhijason
Description
FAQ
Comments (17)
A version is amazing
ComfyUI, Edit 2511
lora key not loaded: transformer.transformer_blocks.59.attn.add_k_proj.lora_A.weight lora key not loaded:
and blah blah blah
same problem
I get this too, with all the A2R models, but it still works. As long as it loads and is having an effect, this is normal. It just means the LoRA doesn't include some keys, likely ones it doesn't modify to begin with, likely for the sake of size.
Patched
You might download the file again with patched suffix
非常好的LoRA，能很好地还原原图的服装、场景！
2061A的版本试下来，在几个方面还是有些限制，如果有后续版本还能在这些方向上加强：
1. 俯拍视角经常只有人脸在焦内，要是能更自由地调节光圈大小和对焦就更方便了
2. 部分人物神态不跟原图，闭眼，张嘴笑等神情做不出来
3. 浅棕色等部分发色，浅绿色等部分瞳色比较难生成
再次感谢你的高质量LoRA！
可以尝试接入vlm反推图像辅助出图，我测试了一下效果还不错
@xiaozhijason 好的，我试试。
不过VLM的描述对场景影响有限，我在想办法调节背景清晰度。
@OnlyWinningMove 其实很大程度上是因为没有描述，所以模型不肯定是什么。如果有描述的话，可能能清晰点。更多的问题是，vlm描述可能会和原图冲突，然后图片根据描述生成而没有参考图像
@xiaozhijason 感谢更新，我也补充一些，无论是第一个版本还是2601A的该lora在任何张口的表情时都会有露出龅牙的倾向，这方面有什么除了闭嘴以外的有效提示词可以解决吗？
还有一些提问，大部分时候我都需要加上“将头部改成小头型、小脸、瘦脸、瓜子脸”等来调整动漫尺寸的宽脸，哪些提示词有效？
以及漫画的速度线，运动线，这些东西有什么好办法消去吗？
关于lora里没有提到哪一个大模型合适，我注意到你的工作流使用的是2511的mixed，但又另加了4步蒸馏lora，请问你用的是哪一个2511？
@kirikirikiri 我主要用2511 fp8mixed和4步的加速，其实可以试试配合别的动漫转真人的lora比如anime2real来增强转写实的效果。
can 16g Vram run this？
12G很轻松！~
I'm running it on 8 (Geforce 2060 super)
This is a fantastic LORA... thank you! One observation: sometimes the resulting image is cropped. Is there a setting to avoid this?
Did you use QwenEditUtils or just load the lora and official workflow?