Run Flux PuLID Locally on comfyUI Pinokio Tutorial | Consistent Characters

preview_player
Показать описание
Welcome to AI Motion Studio! In this tutorial, we’re diving into a powerful tool for AI creatives: the Flux PuLID workflow on ComfyUI via Pinokio. If you’ve ever wanted to achieve consistent facial features across multiple images in your AI projects, this guide is for you! This video provides a step-by-step approach to using Flux PuLID locally on ComfyUI via Pinokio, perfect for anyone creating character-based AI art, movies, or image series. By the end of this tutorial, you’ll be equipped to generate stunning, consistent character images without needing high-VRAM setups.

What You’ll Learn in This Video:
Installing and Setting Up: We’ll walk you through the setup process, from downloading the Flux PuLID and EVA Clip models to setting up the Antelope V2 model for facial consistency.
Step-by-Step Installation: Follow along as we install the necessary dependencies and run commands in Command Prompt to get Flux PuLID fully operational on ComfyUI.
Creating Consistent Faces: Learn how to maintain the same facial characteristics across different images with varying styles, outfits, and settings.
Prompting for Variation: We’ll show you how to use prompts effectively to generate different scenes with your character while keeping their face consistent. From close-up shots to cinematic looks, we’ll create unique images with a consistent character!
Who Is This For?
Whether you're an AI artist, designer, or filmmaker, this tutorial is ideal for anyone looking to maintain consistent character identities across various AI-generated visuals.

Why Use Flux PuLID?
The Flux PuLID model offers a lighter solution than VRAM-heavy methods, like LoRA training, and is accessible even on setups with limited VRAM (8GB GPU compatible). With this workflow, you can bring any character to life in countless settings without the need for complex training.

Example Walkthrough:
In the video, we’ll demonstrate how to use Flux PuLID with a reference image of actress Zendaya. See her in different settings—from sporty styles to cinematic poses—while maintaining facial consistency in every frame. This approach is ideal for creators who want diverse imagery without losing character identity!

Engage with Us!
Found this video helpful? Give it a thumbs up and subscribe to AI Motion Studio for more tutorials on AI tools, character consistency, and image generation techniques. Have questions? Drop them in the comments, and we’ll be glad to help. Stay tuned for our next video on pushing the boundaries of AI art!

#Pulid #ComfyUI #AIGeneration #FluxPulid #ConsistentCharacters #AIArt #ComfyUISetup #CharacterDesign #AIMovies #aiartcommunity #facexlib #Insightface

Commands if you run into PuLID Node Errors:

Рекомендации по теме
Комментарии
Автор

i am confused with the installation of antelopeV2, in the models folder i dont have insightface folder, what to do ?

Gambit__YT
Автор

I get all black output, black image. But i guess workflow works. Any idea what is wrong?

SignINFERNO
Автор

How to have that queue prompt side bar

ronaldlawas
Автор

I cannot find the instalation code that goes into app folder where is it??

larryvw
Автор

system cannot find the path specified at the last part where we install requirements.txt cant find the solution

horus
Автор

What's the difference between reactor face swap?

sylvainderoche
Автор

Hello! Tell me how to fix it?
SamplerCustomAdvanced
forward_orig() takes from 7 to 9 positional arguments but 10 were given

ВладимирБондарь-ть
Автор

I could not achieve facial consistency in my experiments. I think the resolution of the reference image I use has an effect on this. Can you give information about the size of the reference images you use?

cemilhaci
Автор

Thank you for the great tutorial. Only one thing happend to my installation. Load Diffusion Model is just crashing with showing me a necessary reconnect and then it just stops. Do you know what could cause the issue? Havent changed anything in the workflow so far.

UskFreigabe
Автор

At minute 3:29 Mine says path not found. I did change the drive letter to the one mine is installed in.

rickpena
Автор

Thanks for the tutorial. Got everything to work except Insightface. I always get an "Path not Found" error as i am trying to install it via the command termina

StargazerFilms
Автор

Thanks for the tutorial, I was able to set up everything accordingly. But I am getting this error at 73% SamplerCustomAdvanced expected scalar type Half but found BFloat16. Please help :)

kaziahmed
Автор

but can i use images generated using flux dev model commercially??

AIRawFootages
Автор

I have downloaded the pulid model safetensors and placed it in the Pulid folder. But why does it always stop at the flux model Puled node?

Failed to validate the prompt for output 9:

* PulidFluxModelLoader 99:

- Value not in list: pulid_file: not in []

SyamsQbattar
Автор

do you not find that using PulID the face are always facing at the same point as the reference image? and the image seems not that realistic in comparison to using reactor

leonv_photographySG
Автор

This is good but I would love to add the loraturbo for speed, can you tell me whre can I add loras to this workflow?

AIBizarroTheater
Автор

I don't know which windows to bypass, since the quality is to low to read the captions. I tried to figure it out, but then I get a lot of errors.

alinguist
Автор

why wouldnt you put the model in the drive folder instead of the api folder? models are supposed to go into Drive. but im not sure if it can use full structure.

Larimuss
Автор

Awesome tutorial but I am stuck on Load PulID FLux Mod Node, it does not show any models. I am assuming it is looking for What folder should it be in for this node to see it please?

noNumberSherlock
Автор

end results dont look like my characer how to tweak it so my characters face is there, not ai face

islamicstoriesz