ComfyUI beginner friendly Flux.2 Klein 9B GGUF Simple Flawless Fast Headswap Workflows by Sarcastic TOFU

This is a very simple ComfyUI beginner friendly Flux.2 Klein 9B GGUF Simple Flawless Fast Headswap Workflow set that will work with very simple text editing instructions in natural language to swap head of your desired target image's subject from a reference image. I used a Q4 Model that works well with my 8GB AMD GPU. But is you have better GPU you can simply swap the model with full unquantized Flux.2 Klein 9B model or on the other side if you have a weaker GPU you can find other very low grade hardware (with 2GB or 4GB VRAM) supported GGUF models from here - ( Unsloth's HuggingFace repo for Flux.2 Klein 4B GGUF models - https://huggingface.co/unsloth/FLUX.2-klein-4B-GGUF/tree/main ) and other matching resources that you can use on my older Headswap workflow for Flux.2 Klein 4B. This workflow set uses Best Face Swap (BFS) LORA for Flux.2 Klein 9B from NRDX ( https://civitai.com/user/NRDX ).

This workflow set can save your Headswap Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. This workflow set has two files - Flux2k_9B_GGUF_SWAP_v1 (Default Dimensions).json is your simple inpainting & Headswap workflow and Flux2k_9B_GGUF_SWAP_v1 (Custom Dimensions).json is your Headswap with outpainting workflow. You will find all the saved prompt files that it generated with the images inside the Archive (.Zip) that has this workflow set. Also with the Image Saver Simple node used you may embed the workflow itself with each saved image or save the image and workflow for your work separately.

The Flux.2 Klein 4B and 9B models are a new family of high-speed AI image generators that use a "rectified flow" architecture to unify image generation and professional-grade editing into a single, compact package. These models are significantly faster than older versions because they use "step-distillation," which allows them to create high-quality images in just 4 steps—achieving sub-second speeds on modern hardware—rather than the dozens of steps required by previous models. The 4B variant is released under a permissive Apache 2.0 License for both personal and commercial use, while the more powerful 9B variant uses a Non-Commercial License intended for research and personal projects. Both models support 11 native aspect ratios ranging from 1:1 square to 21:9 ultrawide and 9:21 vertical, and they can produce sharp images up to 4 megapixels (such as 2048x2048). To make them even more accessible, there are Q (Quantized) models like the FP8 (8-bit) and NVFP4 (4-bit) versions, which reduce the "brain size" of the model to save memory; specifically, the FP8 version is about 1.6x faster and uses 40% less VRAM, while the NVFP4 version is up to 2.7x faster and uses 55% less VRAM. While you can run the Flux.2 Klein 4B GGUF model on systems with as low as 2GB VRAM to run Flux.2 Klein GGUF model smoothly you would need atleast 6GB VRAM (i.e. Q4 GGUF, the very low end Q2 & Q3 GGUF moel files can't produce quality results, if you have very low end systm with 2GB or 4GB VRAM then you should use Klein 4B GGUF models). I used Q4_K_M file that works well with 6 or 8GB VRAM in this workflow set. This one provide acceptable quality results.

You can download all of your necessary model files used in this workflow set from HuggingFace (Details are mentioned below). Make sure you have latest enough ComfyUI installation and install any necessary nodes for for this workflow using ComfyUI manager and place the correct files in correct places. Also check out my other workflows for SD 1.5 + SDXL 1.0, Pony, WAN 2.1, WAN 2.2, MagicWAN Image v2, QWEN, HunyuanImage-2.1, HiDream, KREA, Chroma, AuraFlow, NoobAI, Illustrious, Lumina2, Z-Image Turbo, Flux.2 Klein 4B, Flux.1 Dev and Kandinsky Image 5 Lite (T2I & I2I) models. Feel free to toss some yellow Buzz on stuffs you like.

How to use this -

#1. Just select your desired Flux.2 Klein 9B GGUF (or swap it with full model) models first and now

#2. now select your image(s) - a target image for face swap & a reference face image that you want to see on your output

#3. on next step enter your image editing instructions only if you have to.. the default prompt simply does the job

#4. then select how many images you want (Change the number besides the "Run" button)

#5. after this select image sampling methods, CFG, steps etc. settings (you may wanna stay with defaults)

#5. finally press the run button to generate. That's it..

**This will automatically detect subject's face and hair, put masks over these and only inpaint those portions leaving rest of image as it is.. cloth, background, postures will remain preserved only head will be swapped. Unless of course you specify which other part(s) of the original image you want to change ( See the Examples named Output-2 and Output-4 to get ideas about how to exactly do so.. and Yes! you can do headswaps for NSFW images )

Required Files

==================

Flux.2 Klein 9B Models -

-----------------------

### Download Link for Flux.2 Klein 9B GGUF Model used

------------------------------------------------------

https://huggingface.co/unsloth/FLUX.2-klein-9B-GGUF/resolve/main/flux-2-klein-9b-Q4_K_M.gguf

### Download Link for Flux.2 Klein 9B Text Encoder used

--------------------------------------------------------

https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

### Download Link for Flux.2 Klein 9B VAE used

-----------------------------------------------

https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors

### Download Link for Best Face Swap (BFS) LORA for Flux.2 Klein 9B from NRDX

------------------------------------------------------------------------------

https://civitai.com/models/2027766?modelVersionId=2610018