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 (5)
It's funny but the result without lora looks better in every image, lol
That why I show the original output. Flux2 Klein is very good at style transfer. It already produce decent output at base model. If you think you like the original more, just use original model.
Its interesting to analyze the similarities between no lora and with lora on the Klein 9B version. In both cases - the first example turns the girl's black hair into grass and the white string in her right sleeve into red. It seems more than anything - the LoRA's effect was to push the model away from realism and into a '2.5D' style.
I think OP should consider updating their dataset with hand-picked, manually-inpainted results from Klein 9B itself (ex: generate a bunch of images, select the best ones and merge the best areas of each one into a single image with manually drawn masks - per sample).
@huj0ps1t6 Using self generated images as training samples is a regulation. As I said, the base model already does a decent transfer, it could ouput in between result by adjusting lora strength. Generate some samples and collect the best of them could further train to the optimal spot in further development.
using this lora(klein) require comfyui update to jan 24 or newer