Put your character into another photo, or swap only the head. It also works when other people are in the photo: say who to replace, and everyone else stays as they are.
It's in my new video: I threw a ton of edits at Qwen Image 2.1, FLUX 3 Klein and FIBO 2
The swaps run on the BFS LoRAs by Alissonerdx (body swap and head swap). The optional Speed LoRA is PrunaAI's 8-step LoRA, converted for ComfyUI by t8star.
How to use it
Load your scene, the photo you want to change.
Load your character, the person you want in it.
In Who to replace, say who gets swapped. With one person in the photo, leave "the person". With more, say where they stand, like "the woman on the left".
Run. The request sent to Qwen shows in Show Text, above the result.
To swap only the head, switch Swap the whole body off. The scene's clothes stay.
To swap two people at once, select the Second character nodes, press Ctrl+B, load the second picture and say who it replaces.
Faster, optional
The Speed LoRA is switched off. Download the file below, switch on its first row in both swap LoRA Loaders (Body and Head), and set Steps to 8. A run drops from about 20 seconds to 8 on an RTX 5090, and in my tests the swap looks the same. Only use 8 steps with the Speed LoRA on. Without it, 8 steps looks soft. Leave Steps at 25 if the row is off.
What you need
AusBoss nodes 2.5.1 or newer. In ComfyUI-Manager, search "AusBoss". Already have them? Update first.
A ComfyUI with Text Encode Qwen Image 2.1. I tested on 0.38.0.
The Qwen Image 2.1 models and the two LoRAs:
qwen_image_2.1_int8_convrot.safetensors →
models/diffusion_models· 7.26 GBqwen3vl_8b_int8_convrot.safetensors →
models/text_encoders· 9.35 GBqwen_image_2.1_vae_bf16.safetensors →
models/vae· 676 MBbfs_body_swap_v1.0_qwen_2.1.safetensors →
models/loras· 210 MBbfs_head_v1.1_qwen_2.1.safetensors →
models/loras· 260 MB
Both LoRA files have to be installed, even if you only use one. ComfyUI checks them when you run.
Optional, for the Speed LoRA: p_qwen_image_2.1_8step_v0.1-comfyui-T8.safetensors → models/loras · 336 MB. The row is off, so the workflow runs without the file.
Tips
Say who by where they stand or by their hair, not by their clothes. For a whole-body swap, clothes you name are kept. "The woman on the right with the braid and yellow top" kept the yellow top. "The woman on the right" swapped it.
Use a character picture that shows the outfit from head to knees, with the hands down. If it stops at the chest, the old legs and shoes can stay. A hand on the face or a peace sign can move into your scene and add an extra arm. A plain background works best.
Keep signs and cups out of the character picture. They can follow the person into the scene.
Whole body takes the character's clothes and build. The scene's pose, light and background stay. Head only keeps the scene's clothes, and on wide shots with small people it barely shows.
If one person comes out wrong, change the seed. Quiet scenes with one or two people sitting or standing work best.
Only use pictures of people who agreed to it. The LoRA's author asks for this.
About 20 seconds a run for one character, 28 for two, on an RTX 5090. With the Speed LoRA, about 8.
If a swap goes wrong
The Add to the request node is switched off. It holds three sentences that go on the end of the request. Select it and press Ctrl+B to switch it on, and delete any sentence you don't need.
The scene's old legs and shoes stay (the character picture stops at the chest): "replace the legs and shoes as well, nothing of the old outfit from <image1> stays."
A hand from the character picture shows up (a hand on the face, a peace sign): "keep the arms and hands exactly as in <image1>."
A sign, cup or other object from the character picture comes along: "do not copy signs, poles, cups or other objects from <image2>."
<image1> is your scene and <image2> is your character. The hands sentence did not fix small people in a wide shot.
Credits
Qwen Image 2.1 is by Alibaba Qwen, under the Qwen Research License: non-commercial use only. The BFS LoRAs are by Alissonerdx, MIT License. The optional 8-step Speed LoRA is by PrunaAI, converted for ComfyUI by t8star, under the same Qwen Research License: research use only.
v1.0 (2026-10-02): first release.
Questions or bugs: GitHub issues or the comments here. Videos on YouTube @ausbossdev. More from me on X @Zanzibased and GitHub.
Description
First release. Needs AusBoss nodes 2.5.1 or newer: already have them? Update them in ComfyUI-Manager first, then restart ComfyUI.
FAQ
Comments (15)
These are amazing and I have no idea why no one else has said so . . .
thank you :’)
state of art workflow design, impressed by your work. really apprecaited.
thanks. i really appreciate that
ive never seen a workflow like this. Its cool as hell.
would a similar workflow but using character loras (for multiple characters) be possible? I guess it would probably need 2 passes to separate the loras
it's freaking revolution
just amazing,a Simple but beautiful workflow
Very good, highly recommended
you've made every learning so much easier. now i know why people do custom nodes.... though there's so much fundamentals to know...
You have any place to recommend to start learning and diving into the rabbit hole?
glad it’s helping! honestly i got into it by making nodes for things i wanted to do and couldn’t. i’d hit something where there wasn’t a node for what i had in mind, so i’d build one. started small, one here and one there, and the ideas got bigger as i got more comfortable.
the best way in is to start with a tiny “hello world” node and grow it from there. once you see what’s possible, you start coming up with ideas you wouldn’t have thought of before.
fundamentals are worth learning, but i think the best way to learn is by doing. pick something you actually want and use whatever tools you can to make it real, coding agents included. if you use one, ask it how things work as you go. you pick up the fundamentals just from grinding on a project you care about.
Your workflows are truly outstanding, I've tried a lot and there are not even close to yours, amazing job 👍🏼. Do you have Kofi or something? Your work deserves more recognition. Only problems are face have nothing to do with the workflow but with the outputs which lack realism but those are issues of the references I use 😂
Newer user here. This works amazingly well. Simple, easy to use, and very impressive results. Thank you!
That's great! The official website has just released a turbo version of the model. Are there any plans to adjust the streaming settings to use this model?
yes, i tried it today. the bfs head and body swap loras hold on the turbo just like on the regular model, in about half the time (around 10 seconds a picture instead of 20 on my card). it isn't a straight file swap though. the turbo needs its own 8 step sampler setup, so the workflow needs an update before you can use it there.




