Allows you to replace a subject in the first control image with a subject in the second control image.
The model will skew towards preserving existing details if the secondary control image does not include the relevant details and the prompt leaves them unspecified. For example, if you are using a head/torso image as the new subject, but the original image was zoomed out more and the person being replaced has jeans, the new person will also be wearing jeans unless you specify otherwise.
For best results, try to have comparable framing, camera angle, and number of subjects in both images.
replace the person in Image 1 with the person in Image 2
replace the man in Image 1 with the man in Image 2
replace the woman in Image 1 with the woman in Image 2Model Comparisons:
Copy Pose will preserve the subject and background in Control 1, while bringing the framing/pose of Control 2
Replace Subject will preserve the framing/pose and background in Control 1, while bringing the subject of Control 2
Replace Scene will preserve the subject and pose in Control 1, while bringing the background scene of Control 2
California AB 2013 Training Data Disclosure
This LoRA was fine-tuned using visual data consisting entirely of synthetic still images. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.
The dataset consists of over 100 image sets (over 300 images total). This is the total used for training after low quality sets were culled. Dataset was created in 2026.
Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset.
This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.
Description
FAQ
Comments (16)
Thank you so much for this!
So is this like the inverse of your pose change lora? Or is it more like a refinement? Both are excellent, just curious as to the use cases.
Yes, this is like the inverse :) Pose change keeps the subject/background while changing the pose, while this one keeps the pose/background while changing the subject. I'm also working on completing the set with one that will keep the subject/pose but change the scene.
@ReltivlyObjectv Well since I've got your attention, I must say, your loras are the most consistent and have the best results amongst any of the toolbox-style loras that are out for Flux Klein. Seriously. If I had enough cash/buzz, I'd shower you in it.
@East_I_Go_Not Thank you! That is much appreciated and great to hear! I'm glad they're working well for you.
While we're here, I'll just throw this out there as an open invitation for you and others: I'm always open to ideas for additional models that you may are lacking in the existing space, be they general purpose or niche utility, so if there's one you'd like me to make, please don't hesitate to ask! :)
@ReltivlyObjectv What about a hairstyle swap lora? The only hairstyle loras that have been published for Flux Klein are for specific hairstyles, it would be nice to have one that's basically "apply the hairstyle from the subject in image 2 to the subject in image 1 while preserving the hair color of the subject in image 1" or something like that. Changing hairstyles is easy without loras but maintaining hair color of the base subject while doing so is practically impossible lol.
@East_I_Go_Not That's a good idea! I will try to make one :)
hey how do you replace the subject if there are 2 subjects on the image?? is this following trigger still work ?
"replace the person on the left side of the frame in Image 1 with the person in Image 2" or do i have to follow the exact trigger word??
You should be able to replace a specific person in Image 1 by prompting something that specifies them. So prompts like "replace the woman on the left in Image 1 with the person in Image 2" or "replace the taller man in Image 1 with the person in Image 2" should work.
@ReltivlyObjectv Thanks
Absolutely love this lora for flux klein, my specific task was to place person from image 1 to room in image 2 and change outfit to image 3, keeping pose and identity from image 1, this lora works very well, thank you!
Is there a recommended workflow for this?
It should work out of the box if you just route the model/CLIP in the stock ComfyUI workflow (both base and distilled work) through the LoRA node. If you drag any of the example images into Comfy, it will show the workflow :) I have a few extra nodes to construct the "A+B=C" preview image, but you can delete those extras and just use the subgraph.
Thanks! Love <3
plz bring a workflow im struggling
It should work out of the box if you just route the model/CLIP in the stock ComfyUI workflow (both base and distilled work) through the LoRA node. If you drag any of the example images into Comfy, it will show the workflow :) I have a few extra nodes to construct the "A+B=C" preview image, but you can delete those extras and just use the subgraph.


