README.md

---
language: en
license: apache-2.0
library_name: diffusers
tags:
- flux
- flux2-klein
- text-to-image
- quantization
- sdnq
- 4-bit
- dynamic-quantization
- low-vram
- google-colab
- t4
- batch-image-edit
- background-removal
pipeline_tag: text-to-image
base_model:
- black-forest-labs/FLUX.2-klein-4B
---
This model is a finetuned Flux.2-Klein-4B model.
The model as been quantized for use on the T4 in the Google Colab environment.
Code on how to use this quantization is provided in this model card ⬇️. 

![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/y6QlxRa4dWMaLf6m9byrh.jpeg)

From: https://civitai.red/models/2327389/flux2-klein-aio?modelVersionId=2618128
(the most popular Klein 4B finetune currently)
---
Step 1: 
To Use in google Colab , first make sure to fill 2 zip files on your Googoe drive called foregrounds.zip and backgrounds.zip

![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/7-55l5qy447qQVasTtC9n.png)

Then run the encrypt cell https://huggingface.co/codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic/blob/main/colab_notebooks/twin_input_setup/%F0%9F%94%93encrypt_kaggle_dataset.ipynb

This will create a folder of encrypted images + settings and the edit prompt for batch processing.

Step 2: 
Then you can either run the encrypted image folder in the run cell for google colab: https://huggingface.co/codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic/blob/main/colab_notebooks/twin_input_setup/dual_pipe_klein_edit_colab.ipynb

Or alternatively , as I prefer it , run the cell on Kaggle: https://huggingface.co/codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic/blob/main/kaggle_notebooks/twin_input_setup/fg-bg-klein.ipynb
Running on kaggle.com has the advantage of using 2xT4 instead of one which are twice as fast (one image edit every 15 seconds roughly , compare to colab one every 30 seconds) , and the script can be run and will auto disconnect upon completion. Unlike the Google colab variant which needs to be kept open in browser.) 


![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/KEtYd63VBdMky6kpWcqc5.png)

![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/caO3nPmO7hhz3tfnt3eJc.png)

Step 3:
Finally , decrypt the results using the decrypt cell: https://huggingface.co/codeShare/FLUX.2-klein-AIO-SDNQ-4bit-dynamic/blob/main/colab_notebooks/twin_input_setup/decrypt_results.ipynb

For this step you need to remember the password in order to decrypt the contents. 

//--//

Output example 

Suppose you have a foreground image of a fashion photo from dollskillz fashion brand: 
![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/rYbHMJveSgl287vqIcJFc.jpeg)

And have this background (you can find alot of gradient backgrounds and such on pinterest): 
![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/Kd076vTtdYztwVJCp1okq.jpeg)

Then , assuming you have an edit_prompt sorta similiar to 'place the character on image 1  on the background in image 2' , the output result from the SDNQ klein 4b edit model as a 1024x1024 square will be 
![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/1U0o6vwBXhvWr2SXZk-c5.jpeg)

//--//

This us the main task I intented of this SDNQ klein 4B version; to process foregrounds and backgrounds into 1024x1024 squares that can be used for lora training text to image models. 

Here are other examples:

![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/w4P1kkBj-W0bQDSsy4fh9.jpeg)


![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/rhN7TsrkjEtr00Qu8qJsq.jpeg)


![image](https://cdn-uploads.huggingface.co/production/uploads/65d7326229af34543a0f4fd0/9q9Fwkl9nGFcCrbBy6p3o.jpeg)