About V1.2;
In this version,
I added a "PERSON SWAP". This is essentially a pose swap, and it works great.
I add 3 variable latent. (Two vae encode and an empty latent) This way, you will be able to set the desired resolution and aspect ratio. It's better "select 1" But what is it?
"Select 1" uses the aspect ratio of Img1 in the resulting output image.
"Select 2" uses the aspect ratio of Img2 in the resulting output image.
In this case, Select 2 is "tool yolo cropper."
"Select 3" Empty Latent Image. Opens a clean page. You determine the resolution.
In other words, you are switching between "VAE encodes and empty latent".
I updated the prompts, organized and simplified the nodes.
About Outfit Swap: Outfit swap is tricky. I admit that the normal regular qwen edit workflow changes clothes better. Just type new prompt that i create. I'm providing it below. Just enter this prompt in the regular qwen edit wf;
"Style the woman in image1, with every article of clothing in image2"
***Qwen 2511 2509 Swap Anyting (head, face, body, outfit, etc..) ***
In this workflow, you can easily swap anything you want with *100% CONSISTENCY** and without node complexity. The chance of facial mixing is ZERO..
Here, I utilized the advanced SAM3 model. You can easily swap faces, heads, just hair, bodies, or a part of an object. Simply type what you want to mask into the SAM3 Text Prompt panel. For example, "woman's head" or "man's hat." Everything you type in the prompt will be masked.
Just upload the relevant images to the corresponding "load image" section. You can use any checkpoint you like. I chose Phr00t and Qwen-Image-Edit-Rapid-AIO because they are very successful. (https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO). You can trust my Ksampler settings because I did a lot of testing.
If you want exactly the same facial expression, Use FP2 LORA and adjust 0.5, 0.6
https://huggingface.co/DiffSynth-Studio/Qwen-Image-Edit-F2P/tree/main
The missing sam3 model will be downloaded automatically. About 3gb
I'm new to this, and this is my first workflow. I hope I haven't done anything wrong.
* HEAD OR FACE SWAP
Prompt Sam3 text2; "The woman's head"
Prompt Sam3 Text1; "The woman's face"
Replace the masked woman's head with the woman of image2. (((Match the head shape, rotation, and color to the image in the source.))). Match the emotions and gaze from the image2. Keep everything else the same.
Enhance skin texture with ultra-sharp with micro-detailes. Neutralize all color casts.
* PERSON / BODY SWAP
(Bypass ToolYoloCropper)
Prompt Sam3 text2; "Person"
Prompt Sam3 Text1; "body"
Transfer the woman in image2, including her body shape and torso, to the location with the green mask in image1.. Ensure that the entire body of the woman in image2 are completely transferred to image1. (((Ensure that the woman in Image1 maintains her body shape and weight))). Match the emotions and gaze from the image2. Keep everything else the same.
Neutralize all color casts.
Make the image ultra-detailed. remove all text.
* ONLY OUTFIT SWAP
*** It doesn't work very well. Instead, use the regular Qwen workflow and enter this prompt: "Style the woman in image1, with every article of clothing in image2." ***
(Bypass ToolYoloCropper)
Prompt Sam3 text2; "The woman's entire outfit"
Prompt Sam3 text1; (leave it blank)
“
Simply replace the masked light green area with the clothes in image1. Copy only clothes from image1 to the person in image2.
Copy all the clothing from image1 to the masked area of the person in image2. Make sure that all the clothes in image1 are exactly the same as those worn by the person in image2.
Do not create new pieces or combine/separate pieces.
Place the clothes naturally on the existing body in image2 without changing the pose, proportions, and silhouette.
Do not change the face, skin tone, lighting, environment, or emotion in image2.
Zero color tone, zero color aberration,
Use the clothes from image1 as they are.” Keep anything else unchanged.
* FOOD, ITEMS, THINGS SWAP
(Bypass ToolYoloCropper)
Specify what will be exchanged in Sam3 text2 and text1.
Replace the masked subject with the image1. ((Match rotation and coloring to the image in the source image)). Keep everything else the same.
Neutralize all color casts.