.jpeg)
This workflow was developed for high-precision head swaps using the Qwen-Image-Edit-2509 model as the editing core.
I spent two weeks testing different node combinations and configurations, going through more than ten versions to reach this result.
About the Workflows
Here’s what you’ll find in the available workflows:
Face Swap V11 – This was the very first version of the workflow, created before I started training any LoRAs.
BFS – Workflow (Focus Head) Advanced – Based on the first version but now using a LoRA. It allows the use of masks and provides more control over blending.
Head Swap V2 Simple Workflow (With Lighting) – A simple workflow for the Head Swap V2 (Focus Head) LoRA, combined with the Lighting LoRA.
Head Swap V2 Simple Workflow (Without Lighting) – The same V2 (Focus Head) workflow, but this time without the Lighting LoRA (LightX2V acceleration).
Head Swap V3 Simple Workflow (With Lighting) – The simple workflow for Head Swap V3 (Focus Head), using the Lighting LoRA. In this version, the order of the input images has changed, and the prompt has also been updated.
Head Swap V3 Simple Workflow (Without Lighting) – The V3 (Focus Head) workflow without the Lighting LoRA. As with the “With Lighting” version, the input image order and prompt are different from previous versions.
⚠️ Note: The Face Swap V11 workflow requires MediaPipe for one of my custom nodes, but it's not yet compatible with Python 3.13. So, if you encounter this error, replace the node with another one or don't use this workflow; these nodes are not necessary for it to function.
BFS - Best Face Swap (Qwen Image Edit 2509) - QIE - V3 Focus Head | Qwen LoRA | Civitai
Face Swap Video Tests:
Face Swap - Qwen Image Edit 2509 (English)
See other examples that I can't post on civitai here: First Workflow
or BFS (LoRA) - Qwen Image Edit 2509 | Patreon
