ComfyUI - The Multi Mode Control Power of FLUX Controlnet Union

The FLUX Controlnet Union is an alpha version AI model by InstantX, designed to offer a versatile and scalable control mechanism for text-to-image generation using the FLUX.1-dev model. Unlike specialized ControlNet models focused on a single control mode, this Union model supports multiple modes such as edge detection, depth estimation, and pose estimation. Although its performance may not yet match specialized models, it shows promise for handling diverse tasks and improving as training continues.
***********************************
Comfyui tutorial, Учебное пособие по Comfyui, Comfyui ट्यूटोरियल, Tutoriel Comfyui, Tutorial Comfyui, Comfyui 튜토리얼
Comfyui stable diffusion, Install comfyui, comfyui video, controlnet comfyui, comfyui animateddiff, comfyui sdxl, comfyui upscale, comfyui video to video, comfyui manager, comfyui inpainting, comfyui ipadapter, comfyui faceswap
***********************************
🤯 Get my FREE comfyui tutorials with workflows: openart.ai/wor...
• CG TOP TIPS - AI MUSIC
/ @cgtoptips
------------------------------------
🌍 SOCIAL
/ cgtoptips
/ cgtoptips
📧 [e-mail]
------------------------------------
#ComfyUI
#Flux
#ControlNet

[@divye.ruhela]

I like how this dude builds his workflows in the reverse order lol.

[@Alex_Niko_Y]

Yes, union models are more convenient to store in a folder ) Thanks 👍 , while watching the video, downloaded the model, I will go to collect the workflow.

[@MilesBellas]

Controlnet Union in Flux! 😀👍

[@diogenescastro]

And changed to the dev model. It works even better😁😁

[@diogenescastro]

Thanks a lot buddy. It works like a charm😊😊

[@geocine]

Hello can you make tutorial for making realistic skin in flux while preserving appearance of Flux Lora

[@seanohaone]

The quality of the images is really good, compared to other controlnet workflow. The problem is that I run into the allocation error randomly and the generation time is way too slow. It will take about from 10 minutes to 1 hour to generate one image with my RTX 4080 Super.

[@kidultchannel]

I got error at depth anything, could you give me some advice on this?

[@artefact.design]

Thank you so much for all your videos. About this one. Is there any chance to make the same but with gguf models and share the workflow ??

[@CgTopTips]

Thanks for your suggestion. I will definitely consider it in my future videos

[@Hackinside]

I'm facing the folliowing error: SamplerCustomAdvanced - not enough values to unpack (expected 2, got 1)

[@prakashjan15]

Hi i tried this file, but facing this issue, whats that mean ? "Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)"

[@Decrypt_Symbol]

👌

[@SuperCinema4d]

How aply pose?

[@vesper8]

Awesome workflow! Thanks for sharing! I'm having trouble running it with 12GB VRAM. I'm using the GGUG unet loader and GGUF dual clip loader with Q5 schnell and Q6 t5 clip... but despite that running this workflow is always running into an allocation error.. any idea why this is happening or how to work around it? Thanks!!

[@CgTopTips]

Could you please share your workflow. I'll test it

[@thibaudherbert3144]

workflow doesnt work and on top of that i don't understand only depth is supposed to work ?

[@vayronny]

What library is the tips tool?

[@YoungBloodyBlud]

Need face id for flux

[@philippeheritier9364]

Thanks, but it takes for ever to render even on my RTX 4080 after half an hour im at 35%

[@Radarhacke]

Where to get and where to put flux-dev-controlnet-union model???

[@loquacious1956]

If you watch the video it shows you exactly where to get it and where to put it.

[@vesper8]

6:21

[@romeovazquez7424]

very very long to generate with 4060 ti 16gb

[@benyaminaria283]

work on NF4 Model?

[@CgTopTips]

I haven't tried it, but I don't think there will be any problem !

[@ufuktulga]

i am getting this error Error occurred when executing DepthAnythingPreprocessor:

[@CgTopTips]

Please share the error message

[@ufuktulga]

@@CgTopTips i share some of it above do you have discord or something?

[@CgTopTips]

Please send via email

[@asdfg1346on]

everything related to comfy ui and image generators in general is so dumb made and bad designed. its literally imposible how hard and badly designed it is to learn to use these shit tools

[@ufuktulga]

i load your workflow but still same ''[Errno 2] No such file or directory: 'D:\\stable-diffusion\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\LiheYoung\\Depth-Anything\\.cache\\huggingface\\download\\checkpoints\\depth_anything_vitl14.pth.6c6a383e33e51c5fdfbf31e7ebcda943973a9e6a1cbef1564afe58d7f2e8fe63.incomplete'''