Instead of loading a usable flux model like a regular checkpoint, if you have already downloaded unet flux before, you can use this workflow to create your own checkpoint.

Check out more detailed instructions here:

Flow to combine Flux, you can mix it as you like but my suggestion is:

Dev with Dev: you will create Dev .safetensors but run as normal checkpoint.

Dev with Schnell: speed up loading, acceptable quality. (should do if you have no other option to use, otherwise use Dev).

How to do:

1. Upgrade Comfy UI to the latest version, there is a new button called ModelMergeFlux1.

2. Create a button called ModelMergeFlux1, you choose VAE, UNET and Flux as usual like in the picture or download this:

3. Click create and wait for it to merge into a .safetensors model.

4. Load the workflow normally and start enjoying :3

Negative prompt: like SD sometimes works, sometimes doesn't, in my test, keywords like: watermark, text, logo, color,... work 50/50. Some more specific things like the Disney logo can be recognized and removed (I think so because when I tried, the logo was lost and replaced with something else or nothing).

If you have a better way, please share more, thank you.

Note: It works well with FLUX.1-Turbo-Alpha, LORA human face. 👤✨

Useful and FREE resources:

❤️Free server to make art with Flux: and Tensor Art and

✨ More FLUX LORA? List and detailed description of each LORA I implement here:  

🆕 First time using FLUX? Explanation and tutorial with A1111 forge offline and Comfy UI here:

🛠️ How to train your LORA with Flux? My detailed instructions are here:

❤️ Donate me (I would be really surprised if you did that! 😄):

Find me / Contact for work on:

📱 Facebook: @maitruclam4real 💬 Discord: @maitruclam 🌐 Web: