- Видео 20
- Просмотров 22 536
ComfyUI Workflow Blog
Добавлен 2 сен 2024
I'm an AI developer, and in this channel, I'll be sharing my knowledge While I'm not an expert (yet!), I'm always learning and growing, thanks to amazing resources like RUclips. Share my knowledge how to create AI tools, and All about ComfyUI workflows that I've developed.
I’m not a good narrator yet, nor a good storyteller, but if I keep trying, I will get better in the future.
So if you like my channel Subscribe it
I’m not a good narrator yet, nor a good storyteller, but if I keep trying, I will get better in the future.
So if you like my channel Subscribe it
ComfyUI Flux: Blend 8 Images Into One With Perfect Lighting and Custom Composition Workflow
Hey, I have created the workflow, in which you can combine multiple image and drag and rotate where you want to place it.
First I try SD1.5 has per documentation but not get results what i want, so I Created a new workflow with flux model
Comfyui composition With the Compositor Node you can:
Pass up to 8 images and visually place, rotate and scale them to build the perfect composition.
Group move and group rescale the images. choose your transform center (corner, or center by using ctrl)
Remember the position, scaling values and z-index across generations and easily easy swap images.
Use the buffer zone to park an asset you don't want to use or easily reach transformations controls
Clearly see t...
First I try SD1.5 has per documentation but not get results what i want, so I Created a new workflow with flux model
Comfyui composition With the Compositor Node you can:
Pass up to 8 images and visually place, rotate and scale them to build the perfect composition.
Group move and group rescale the images. choose your transform center (corner, or center by using ctrl)
Remember the position, scaling values and z-index across generations and easily easy swap images.
Use the buffer zone to park an asset you don't want to use or easily reach transformations controls
Clearly see t...
Просмотров: 548
Видео
ComfyUI Image to Video Workflow Tutorial: AI Latest: Convert Images to Videos with CogVideoX-Fun
Просмотров 1,2 тыс.2 часа назад
In this video, I’ll walk you through how to easily convert images into realistic videos using the ComfyUI Image to Video Workflow. Whether you're new to AI or an experienced user, this step-by-step tutorial will guide you through creating stunning animations from still images. We’ll use the latest tools like ComfyUI Animatediff and Stable Video Diffusion to transform your images into videos. I'...
ComfyUI Flux Upscale:- Using Flux ControlNet Tile & 4x Upscale Simple Workflow
Просмотров 1,5 тыс.4 часа назад
I have created is a basic flux tile controlnet workflow, powered by InstantX's Union Pro. Currently, it is the only tile controlnet out there. Tile is a great option to have when trying to upscale an image to super high quality. Try it out for yourself! Whether you're working with low-resolution images or blurry content, Tile ControlNet is an excellent tool for enhancing them to stunning HD qua...
Flux Realism LoRA Workflow Tutorial | ComfyUI Flux.1
Просмотров 8517 часов назад
Hello I have create a Workflow which Enhance your Flux Model using FilmPortrait Lora, in this video you Learn how to enhance your AI art using the Flux Realism LoRA model in ComfyUI! In this detailed tutorial, we'll guide you step-by-step through the Flux.1 workflow, showcasing how to integrate FilmPortrait LoRA for stunning, realistic image generation. Perfect for anyone looking to master AI a...
ComfyUI FLUX: Replace Any Video Background with Flux Model Segment Anything 2 Workflow
Просмотров 5749 часов назад
In this video I Have created a Workflow that Replace the Background Using Flux Model, Step by step how you can do this. ’ll show you an efficient workflow for removing video backgrounds with a combination of Florence, SAM (Segment Anything Model), Flux, and ControlNet. Learn how to seamlessly isolate subjects and replace backgrounds with AI tools that produce professional results. 🔧 Key Steps C...
FLUX ComfyUI: Create Realistic Images with Fine-Tuned AW-Portrait Model Workflow
Просмотров 86412 часов назад
I have created a workflow of FLUX ComfyUI: Create Realistic Images with Fine-Tuned AW-Portrait Model Workflow, In this video, we explore how to use FLUX ComfyUI to create stunning and realistic images using the fine-tuned AW-Portrait model. Learn how fine-tuning the FLUX model enhances image quality by improving lighting, texture, and composition for more lifelike results. We also demonstrate h...
ComfyUI: How to Create Keyframe Animation with Face Control Rig | Advanced Live Portrait
Просмотров 78816 часов назад
In this Video Step by step tutorial how to use this worflow, Using Advanced Live Portrait Node, This workflow help in creating keyframe Animation. Keyframes: Keyframes are points in your animation where you tell the computer what the face should look like. Then, the computer will automatically move the face between these keyframes. Download the workflow: [link] 🔔 Don’t forget to like, subscribe...
Flux ComfyUI Convert Text to Video Workflow | Using Flux Workflow
Просмотров 1,6 тыс.16 часов назад
In this Video, Flux ComfyUI Convert Text to Video Workflow | Step By Step We try to Create A workflow that can convert text to video using Flux Model, Cog5B So much better then this min_cfg for better results, recommended value: 1-5 For better result 🔹 Steps Covered: 1) Setting up the ComfyUI interface. 2) Loading the Flux1-dev-fp8.safetensor diffusion model and weights. 3) Using VAE and Dual C...
ComfyUI Flux: How to Create Your Own FLUX LoRAs Using Flux Gym: Low VRAM
Просмотров 1,2 тыс.19 часов назад
I have created a video teach how you can create your own LoRs using FluxGym if you having very low VRAM Discover how to effortlessly create custom FLUX LoRAs using Flux Gym's user-friendly interface. With support for low VRAM (12GB, 16GB, 20GB), Flux Gym combines the simplicity of the AI-Toolkit WebUI and the power of Kohya Scripts. flux lora training local This step-by-step guide covers instal...
ComfyUI Upscale Flux : How to Upscale Blurry Image High Detail Image Using Supir and Flux
Просмотров 1,4 тыс.21 час назад
I have Created a Workflow, for ComfyUI’s, Flux Model Help in Upscaling that allows you to transform blurry images into sharp, high-resolution photos. In this tutorial, I’ll show you how to upscale blurry images into high-detail, crystal-clear photos using ComfyUI’s Upscale Flux Workflow along with the Supir tool. If you’ve ever struggled with low-resolution images, this step-by-step guide will ...
ComfyUI Text-to-Video: Create Videos Like Runway Gen-3 with 8GB VRAM Text to Realistic #comfyui
Просмотров 1,8 тыс.День назад
Hey I am having VRAM 12GB, Can't able to run CogVideoX-5B so I create a Workflow with the Help of this You can Generated Text to video if you are having Low VRAM Like 8GB Yeah 12GB. I'll walk you through the entire workflow step by step, explaining everything in simple, ► For Daily | Workflows | News | Tutorial ► comfyuiblog.com/ Note: Their error is coming while running, just run it again Hey,...
ComfyUI: Perfect Lip-Sync & AI Face Animation! Bring Any Portrait to Life with AI Live Portrait
Просмотров 2,1 тыс.День назад
In this Workflow I Created Perfect Lip-Sync & AI Face Animation with the help of ComfyUI"Learn how to create perfect lip-sync and face animations using advanced AI tools in this step-by-step tutorial! In this video, we explore how to use ComfyUI, Mimic Motion, and Live Portrait to animate any face, syncing lips with audio for stunning results. Whether you're a beginner or an experienced creator...
ComfyUI Kolors Model AI: generates large-scale images with just one node ComfyUI #comfyui
Просмотров 592День назад
Hello, Today In this video You can Learn how to generate large-scale images backgrounds in ComfyUI using just one node! In this tutorial, we explore the Patch Model and DownScale node to create stunning 2048x960 images, going beyond standard SD1.5 and SDXL models. Discover key parameters like block number, downscale factor, and more to enhance your creative workflow. Don't miss out on tips for ...
ComfyUI Portrait: Create Stunning AI Portraits with ComfyUI Portrait Master Step-by-Step #comfyui
Просмотров 4,6 тыс.День назад
Hey, in this video, I'll show you how to use the ComfyUI Portrait Master node to create amazing AI portraits. I'll walk you through the entire workflow step by step, explaining everything in simple, easy-to-understand language. Whether you're new to ComfyUI or just want to improve your AI portraits, this guide will help you get started and master the process. Let’s dive in and create something ...
ComfyUI:- How to Double Your Workflow Speed with These Expert Tricks #comfyui #comfyui
Просмотров 59214 дней назад
In This Video I share a ComfyUI Trick with the help of This this Hack you can double the speed of ComfyUI Run Flux. ► For Daily | Workflows | News | Tutorial ► comfyuiblog.com/ you can significantly enhance your workflow efficiency. Whether you're a beginner or an advanced user, this trick will help you boost productivity. Hope this video is helpful for you!
ComfyUI Flux: Step-by-Step Guide to Creating a Comic with ComfyUI #comfyui #comfy
Просмотров 56314 дней назад
ComfyUI Flux: Step-by-Step Guide to Creating a Comic with ComfyUI #comfyui #comfy
ComfyUI: - How to Convert Video and Images to Text Using Qwen2-VL Model in ComfyUI #comfyui
Просмотров 29614 дней назад
ComfyUI: - How to Convert Video and Images to Text Using Qwen2-VL Model in ComfyUI #comfyui
ComfyUI: How to Create a Consistent Character Story in 1 Click with ComfyUI | Easy #comfy #comfyui
Просмотров 92414 дней назад
ComfyUI: How to Create a Consistent Character Story in 1 Click with ComfyUI | Easy #comfy #comfyui
ComfyUI Flux: How to Run Flux on ComfyUI with Less Than 4GB VRAM #comfyui #comfy
Просмотров 63614 дней назад
ComfyUI Flux: How to Run Flux on ComfyUI with Less Than 4GB VRAM #comfyui #comfy
ComfyUI:- Advanced Live Portrait without Video Workflow #comfyui #comfy
Просмотров 1,3 тыс.14 дней назад
ComfyUI:- Advanced Live Portrait without Video Workflow #comfyui #comfy
When I run this, my resulting image looks absolutely awful. It's a bit burry and totally destroyed the face of the man in the starting image. This ControlNet must be pretty weak.
No matter what I did, the shadow under the photo does not look natural.. what should I do, what should I manipulate?
Nice ❤
not same face, a different man in upscale, the main problem with all these tools, which preventing to use for any serious restoration. It makes "eye candy" result as usual-the core script of all this Ai, but nothing related to original.
where is the controlnet model??
in description
hi, do you know any model for comfy ui so we can create ai avatar speaker? i am searching for a comfy ui model that i give him a photo (my avatar) and a voice file , then comfy ui give me ai avatar speaker with lip+eye+face synce. i know there are websites to do it but i want to make it in my local pc for free. i have pretty good gpu.
Hey How to use the workflow? Where do I need to put the downloaded workflow?
I want to start using comfyUI. Currently I'm using swarmUI, it's backend is ComfyUI. I'm able to open it but after creating nodes and going forward it just gives error could not detect model type
just noticed, all the asset names are changed to "diffusion_pytorch_model.safetensors"
hm... for some reason it is giving my images a bit of a double vision / blur... it's not as sharp. is this a gguf thing?
Let it be know that this is a workflow for SUPER LOW Resolutuion sub 512, so this is a great help if you are upscaling a image of a scanned stamp. It will not work with even basic 832x1216, so do not get fooled.
Where to download the Fun5B models ?
it will download automatically when you run the program
Audio syncing is the only issue, can you update it as soon as possible?
sure we will
what do you mean by low VRAM ? below 8 GB ? below 16 GB ?
In the CogVideoXFun Sample, make sure the base Resolution is 512
Thank you for the video. My Gym is creating samples but no Loras are made after the steps are completed. Can you offer any advice? I have 10.24 gb ram so I'm wondering if that is the issue. Thank you.
If the process is complete, you need to check the output folder. According to the documentation, the minimum VRAM required is 12 GB.
Thank you for sharing your workflow! Liked and now subscribed.
Thanks for the video. I get this error: "KSampler: mat1 and mat2 shapes cannot be multiplied (1x768 and 2816x1280)" Can you please help, what should I do? my image is 1888x1056px
yes, it is due to the image size,, this workflow is best of Blurry images.. has you mention sizer of image is 1888x1056px You the image is already Optimized... not work on this Resolution, Your can try Supir For that...
@@ComfyUIworkflows Many thanks, I will try 👍
@@ComfyUIworkflows I don't think that is the issue. There is something wrong in this workflow. I tried multiple image sizes from 512x512 down to 66x66 and I get this same error every time. All these images were under 100kb and were low quality. Please do some testing and quality control when putting out your information so you're no wasting people's time.
@@helveticafreezes5010 The workflow is working.. tested.. what error you getting in cmd & make sure dual clip loader type is flux
Hello Where to download all these models I go to the same place you show where it says “resources” on huggingface, but there are only models “diffusion_pytorch_model.safetensors”.
huggingface.co/Kijai/flux-fp8/tree/main huggingface.co/lllyasviel/flux_text_encoders/tree/main huggingface.co/nerualdreming/flux_vae/tree/main. here are the check point and Text Encoder File.. & VAE
Thanks a ton for this workflow and tutorial, I just need to find the right clip models and this should work for me !! It's unfortunate that I never downloaded any of the clip models used here, so I gotta look for them
Great tutorial! I wonder if it can run on 12GB VRAM. When placing nodes, can they be connected in order? It's hard to follow. Is it possible to keep workflows neat and tidy using groups? Thank you
yes, i can run on 12GB VRAM
You should be upfront about how much VRAM this workflow will need. You're not going to be able to run this locally without at least 24GB of VRAM.
@@ZERKA-p4b it will work if you have 6 GB VRAM You have to use GGUF Loader
I am running this on a 8gb 4060,takes a while but it works just fine !! Besides he did mentioned the 2 variations at the start of the video.
Get the same good result without the LoRa. Flux.1-dev dont need any foto-loras. Just prompt what you want to get.
their is a Difference
This is impressive work and I'm surprised that there are no comments. Thank you for this powerful UI and integration of Qwen.
Hello, where i can download the workflow?
comfyuiblog.com/flux-realism-lora-workflow/
@@ComfyUIworkflowsThanks 👍
Was looking for something just like this. Great work!
I want to add this Worklow you shared to Lora, where I trained my own face. How can I use this model finetuned with Lora? How to add it from the menu? Thanks for sharing.
open load lora , select the file you created...
Sorry to say this but from the examples shown they made it only worse. I'd rather prefer someone fixing this annoying banding issue that Flux has. I like Shakker's detail lora though.
you have check the skin details.. by zooming the image... it's look more natural..
hello Everything was ok, but this error is given in the sampler.(object has no attribute Size). How can it be solved?
in your cmd prompt full error
Thank you for your attention, but I do not understand your answer. Can you explain more?
great, thank you, let me know when you revise the workflow to syn audio and lips. by the way its a very nice workflow. thanks for your effort. Have a nice day SIR !!!
Will updated
Thanks
I'm seeing so many of these videos for Supir but not a single person has shared the workflows. I am sick and tired of just going through an explanation for this, can someone share the damn workflow for this
I Used Flux to to do this.. i m working on creating a simple
@@ComfyUIworkflows yeah I realised you're using flux but that initial workflow you used, it's no more available on their official website. I've been looking for the workflow through so many of the supir tutorial but not a single person has shared it.
@@lucifer9814 ruclips.net/video/MPWS6Gz92CE/видео.html
Great work, bro. Can it work on my rough sketches?
Yes, definitely
I try and it freeze at line 136. about 8hrs. 3060/12gb step 1560 8%|▊ | 1/13 [00:00<00:06, 1.91it/s] 15%|█▌ | 2/13 [00:00<00:01, 7.57it/s] 31%|███ | 4/13 [00:00<00:00, 11.23it/s] 46%|████▌ | 6/13 [00:01<00:00, 11.51it/s] 62%|██████▏ | 8/13 [00:01<00:00, 11.49it/s] 77%|███████▋ | 10/13 [00:01<00:00, 11.56it/s] 92%|█████████▏| 12/13 [00:01<00:00, 11.51it/s] 100%|██████████| 13/13 [00:01<00:00, 8.05it/s] [2024-09-15 21:11:14] [INFO] 2024-09-15 21:11:14 INFO move vae and unet to cpu flux_train_network.py:208 [2024-09-15 21:11:14] [INFO] to save memory [2024-09-15 21:11:15] [INFO] 2024-09-15 21:11:15 INFO move text encoders to flux_train_network.py:216 [2024-09-15 21:11:15] [INFO] gpu [2024-09-15 21:11:27] [INFO] 2024-09-15 21:11:27 INFO [Dataset 0] train_util.py:2349 [2024-09-15 21:11:27] [INFO] INFO caching Text Encoder outputs train_util.py:1111 [2024-09-15 21:11:27] [INFO] with caching strategy. [2024-09-15 21:11:27] [INFO] INFO checking cache validity... train_util.py:1117 [2024-09-15 21:11:27] [INFO] 0%| | 0/13 [00:00<?, ?it/s] 100%|██████████| 13/13 [00:00<?, ?it/s] [2024-09-15 21:11:27] [INFO] INFO caching Text Encoder outputs... train_util.py:1143 any idea please
can you check Stable Video 4D?
Checking
Are you considering doing a workflow on restoring and coloring old damaged photos?
yes, soon
thanks but honestly useless model, allocation error on 3080 10gb even with 2b and 16 frames , so its better to use ddm tiled workflow example from kijai
hey, if you get allocation of memory wait 10 sec and run prompt again
it's work, thanks again.
You're welcome!
Hello 👋 Can I Use Story Diffusion With Openpose to create consistent animation.. Plz Reply
yes, you can..
@@ComfyUIworkflows How to do this..
@@MrZuhaib69 for everything do auto we have to create new workflow... but you can do it given animation ti different different image and combine..
@@ComfyUIworkflows plz help me to create new workflow...
@@ComfyUIworkflows Brother plz help me to create story diffusion with openpose
do you think it is worth to try to use it with a 3060ti 8GB VRAM ?
no
how can we have a picture with both characters ?
use both character name in same line
What about image to video?
soon
text to Vedio....? 🤣😂
Nice bro
Hey Buddy Can I use controlnet open pose with story diffusion
yes you can
Can you tell me the total size of the FluxGym folder after downloading all the models and necessary files? My drive already has low capacity with a lot of various models and LoRAs installed. I just want to make sure I have enough storage left for FluxGym.
40GB May be
FluxGym ui sdxl model traing work?
it's not for sdxl
You added the character at 3:41, then it feels like the video just ends abruptly and we don’t get to see the result of adding that new character
you can add character [Your charactername]
@@ComfyUIworkflows Doubtful. I've entered mascot names recently into other workflows and the AI doesnt know who that mascot is or what they look like so it produces some ridiculous image that doesnt look anything like the sport mascot that I'm thinking of. Then I even train an SD 1.5 lora (with 10 images) to recognize what the mascot looks like and it still gets it wrong
The voiceover in your video says, “The best part is you don’t have to use complicated terminal command”, then it proceeds to show nothing but terminal commands for the first seven minutes of the video. If the viewer has no coding experience, this might be complicated for them
Thanks for the feedback! The old method was definitely harder, especially for low VRAM setups. But if you’re using ComfyUI, this method is much simpler - you just need to copy and paste and follow each step. If you run into any issues or need help, I’ll be happy to assist!
@@ComfyUIworkflows is this possible on mac silicon? is there an optimization step for mac silicon? will it work with 16gig ram on mac m1 pro?
@@flethacker no
@@ComfyUIworkflows How about on mac m3 max 32 ram?
Thank you for the great video~!