Flux ControlNet - Easy Install Guide 

Get my 3 WORKFLOWS here: www.patreon.com/posts/flux-controlnet-110607421 My Flux Install Guide: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-tXO6SJ-6Eb8.html My IPAdapter Install Guide: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-KXxk_bGDCzc.html Join my Discord: discord.gg/XKAk7GUzAW

This is great, very clear! Is it possible to combine ControlNet with IPAdapter to match the style of a reference image?

Thank you so much, especially for the GGUF, not having enough VRAM is like gambling, sometimes it renders in 2 minutes, sometimes it stucks loading because system is running out of memory

I still like 1111, but comfy is growing because of how you can load workflows

Thank you Olivio, this is just what I needed. ❤

Word "ComfyUI" and "easy" should not use in same context. Nothing is easy in ComfyUI.

Can you make a video on Forge, now that its soooo much better and has a ton of new features?

Controlnets don't work in ForgeUI for those wondering, developer has a bias for comfyui and is toxic node network akin to blender nodes.

Can you do a comfyui flux inpainting tutorial

Hey olivio ! One question : is it possibke to have consisten character with flux and comfy ?

Thanks as always! Great information!

Watching Olivio while I train my first SDXL LoRA :) How do you show the extension name above the node 6:20? I'm all in with ComfyUI, started with A1111 of course because it's easy, but Comfy is way better and more flexible.

Error : No module named 'controlnet_aux' (ControlNet) (I'm using Flux1-dev-Q4_K_S + comfyUI + Controlnet) There is a error during the node "Canny edge" : "Error occurred when executing CannyEdgePreprocessor : No module named 'controlnet_aux' I re-installed ControlNet auxiliary model manually several times, and updated everything. It didn't change anything.

Hi! I did everything like you said, but the xlabs folder is not showing up in my models folder

Silly Question: its been a while since anyone made an up to date update of which Checkpoint Models can render human faces and bodies the very best in august 2024. You have seen and used so many different ones, which one is your goto model to get 100% real Photos of human beings, disregarding all cartoon stuff in this quest /question. ? is it still juggernaut or realistic or pony? Pony seems to be 10% all cartoon anime in it i saw.... what model would You use? i have tried some Loras of a Singer friend of mine with different checkpoint models. but have not found a number one photo realistic one yet... with or without Lora applied to it

Hi! Thanks for the video ! How come we cannot choose the method + sampler like Euler + beta for example with the X labs sampler?

i started comfyui with all the recommended setting but still getting failed to allocate (low VRAM), despite have 16GB of VRAM on my 4070ti. Is there another method to resolve this?

Does it work SD-Forge? No... it does not

Is this outdated now that Union Pro control net is out?

I never got ComfyUI to do anything... at all... not even run the demo project... so I just installed FLUX with Pinochio Not a whole lot of options with the web UI that way... like a way to pass it an image to base its generations on. Most of these AI user interfaces and installers... are incredibly... not well thought out, and getting more fractures and spreading out as tree branches to be abandoned... every day. They're all their little fiefdom isolated tools, and not building one big single AI, and then adding talents to it...

I know this may sound dumb, but am still a huge fan of A1111 and SD 1.5... so many options now it gets confusing. Should I scrap A1111 and move to Flux? Will Forge controlnet work as well as with A1111? Just when you get things figured out, something new comes along lol

Everything seems to work fine for me, but I'm getting no image, just a black square. Any ideas...?

I am not able to download or install controlnet for stable diffusion, neither on my PC nor on my laptop I also tried it on my friends laptop, and it didn’t work Is it because of antivirus? Have anyone faced similar problem? Need help

how can we control 2 loras, separately. especially if it is 2 person, and each of them has own lora?

ComfyUI for FLUX, everything else Fooocus, especially inpaints. Tried Forge to work with FLUX, for normal use it works like a charm, but whenever lora and others kick in, it starts to mess up with VRAM which leads to being very unrealiable.

I'm surprised how little I've heard about Swarm or Forge in the past 6 months. Does anyone out there use them for their daily driver?

Does it work with Multi Controlnet? Also does it work with Depth Anything V2?

With all this flux hype I would very much appreciate tutorial on how to easily install more vram to be able to run it at all.

So you cant Control the Denoising strength right?

Foocus and Forge!

can we combine it with inpainting?

can we use flux dev controlnet for schnell model

I am using Forge. But I have a question: Is Flux really slower than SD1.5 when aiming at higher resolutions? If i want to end up with an 2MP picture, i can render this directly in Flux, SD and SDXL would most likely need to be upscaled or similar techniques. So lets say 1920x1080 render in Flux vs. in SDXL...What is really faster i wonder. By the way no controlnet for Flux in Forge, right?

Isn't a v3 of the controlnets already available?

so far I like A1111 the most, forge is a little faster but it wasn't working with some of the extensions so not really worth a few seconds faster. just now learning comfy ui and boy is it not comfy to learn lol, I can see it having lots of specific uses but not having images for the loras or models is annoying since many are named random things and looking at a picture, list of tags, and having a direct link to its civitai page is faster and more plesent to use in A1111 than trying to rename a bunch of loras to make sense in comfyui

AllI read is that this is Flux Dev controlNet and not Flux Schnell.

Thanks for the vid, anyone know how to use img2img and controlnet with the Xlabs sampler?

Just need animate diff now and we have a new 1.5. :P

WHY are there 4 prompt boxes? What do they do? Ugh

Comfyui definitely !

Can you test IP adapter for flux?

For some reasons, its works but all results looks like a painting, not photo real

I will have to see about installing the low memory models as I can not any renders to complete as I keep getting the "torch.cuda.OutOfMemoryError: Allocation on device" error. This is with a fresh install on a computer with a nVidia 3080 with 32GB of ram.

Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same error from MIdas Depth Map :( dont know how to solve this :(

No folder, that shold be at 1:53 . Done, and redone couple times. Not work.

Rtx 3060 8gb vram.....flux won't even move forget about flux controlnet😢

Thanks, unfortunately, I only have 6 VRM

FORGE FOR THE WIN

Is it possible to use control net without xlabs sampler? Its very bad and image looks fried like with very high CFG.

uh what about a forge tutorial please?

Flux is cool but it’s like 10x slower than SD 1.5

CUSHY with Comfyui

I use ComfyUI 30% of time, but still use A1111 70% of time.

forge, its just faster and easier to use

Next vid on how to train custom lora for flux? :) locally :D

Ugh another Comfy tutorial. Dislike. ForgeUI is better

ComfyUI