About V2; Only python 3.12. If anyone runs this node on Python 3.13, can they share it with me?
I gave up on the problematic original Sam3 node and switched to the "Easy Sam3" node
***Please upgrade your photobuf and mediapipe for "personmask" ( python_embeded\python.exe -m pip install --upgrade mediapipe protobuf google-cloud-videointelligence )***
Create Your Influencer Face From 3-Images.
Yes, this time it worked, and I wanted to dedicate a separate section to it. In my previous workflow, I created a face from two images but couldn't quite achieve what I wanted. This time, I was truly successful in creating a unique face.
This is a simple workflow for generating new, unique faces. It uses SAM3 to mask specific features (like the nose or mouth) from a source image and then builds a completely different face around those parts. Good for creating character variations or unique identities. You can freely decide which parts of the face to mask. Simply write it in the prompt of the Sam3 model. Keep in mind that some faces are quite dominant, and the model may draw too much inspiration from them. You may need to apply more masking (restrictions).
Why did I need it? Because Pulid and Reactor weren't satisfying me in this regard. Face ID was creating unrealistic faces. Is this workflow more successful than those? You decide. Sometimes AI when trying to fit the mouth and nose into masked areas, a situation different from the reference ones may arise. IDK. Maybe someone will be inspired and develop it further in the future.
How it works: SAM3 Masking: Automatically selects facial features to keep as a reference.
Generation: it tries to create a new person using the unmasked parts.
Quick Guide:
Upload your source image.
Use the SAM3 prompts to choose which parts to keep.
If you like my work, you can buy me a coffee!
Description
FAQ
Comments (12)
IT works with Klein 4b and Klein 9b.
It also works with LORA's.
Nice job!
thanks!
Doesn't work for me. I get an error message and a red node in Draw Mask (img1): "Prompt output failed validation. DrawMaskOnImage. Failed to convert an input value to a FLOAT value.
Could there be a missing node on your WF? If so, you can install it from the "Install Missing Node" section in the "Manager." Alternatively, you may have entered incorrect values in the parameters or they may have become mixed up. In this case, you should download and install it again. By the way, sam3 is a new model, and you need to perform an "Update All" from the Manager. Also, run the update.bat file.
@ugurdoyduk341 There are no missing nodes. I didn't alter any parameters. I ran it as it came after adding the three pics. It's a brand new install, so sam3 should run fine. There is no update.bat file. It's not the portable version I'm running.
@jesper123160 Could you please send me a longer version of the error message from the terminal?
This is cool, it's like the Weird Science build a woman software 2D version.
exactly what I want to do :D
Works far better than I thought. Even faces that are 512 x 512 render true to the original results. Very cool.
Thanks!