ComfyUI AnimateDiff Part 1 - Tutorial
Vložit
- čas přidán 6. 07. 2024
- First part of a video series to know how to use AnimateDiff Evolved and all the options within the custom nodes.
Documentation and starting workflow to use in ComfyUI is available in:
📡 AnimateDiff Evolved: t.ly/GDR_Y
Workflows examples available at: ko-fi.com/s/f16bccaff4
🕸️ Discord: / discord
#animatediff #comfyui #stablediffusion
============================================================
💪 Support this channel with a Super Thanks or a ko-fi! ko-fi.com/koalanation
☕ Amazing ComfyUI workflows: tinyurl.com/y9v2776r
🚨 Use Runpod and access powerful GPUs for best ComfyUI experience at a fraction of the price. tinyurl.com/58x2bpp5 🤗
☁️ Starting in ComfyUI? Run it on the cloud without installation, very easy! ☁️
👉 RunDiffusion: tinyurl.com/ypp84xjp 👉15% off first month with code 'koala15'
👉 ThinkDiffusion: tinyurl.com/4nh2yyen
🤑🤑🤑 FREE! Check my runnable workflows in OpenArt.ai: tinyurl.com/3j4z6xwf
The best ai animation tutorial!
Learn how to make comfyui animation workflow
and use controlnet stable diffusion prompts
ComfyUI: best open source animation software for pc
============================================================
In this video, we start with a txt2video workflow example from the AnimateDiff evolved repository. After a basic description of how the workflow works, we adjust it to be able to use Generation 2 nodes.
After a basic indication of how to use the different models and loras, we delve into the different possibilities to use in the AnimateDiff Apply Advanced node: scale and effect multival; AnimateDiff keyframes and the use of start and end percent.
In the next video, we will learn the construction of comfyui video to animation, prompt travelling, controlnet and the use of context options and sample setttings. All in one video is too much, so better to split it in two.
I hope you enjoy it!
============================================================
📡 AnimateDiff Evolved: t.ly/GDR_Y
🕹️ AnimateDiff paper: t.ly/F6BeZ
💃 Checkpoint ReV Animated v1.2.2-EOL: tinyurl.com/56wpc7v2
🔖Chapters
============================================================
00:00 Intro
00:38 AnimateDiff Evolved (Github)
01:24 Workflow Description (How it works)
03:35 Using Generation 2 AnimateDiff
04:37 Motion models
05:33 Beta schedule
06:24 Motion Loras
08:10 Scale Multival
12:46 Effect Multival
17:02 AnimateDiff Keyframes (AD Keyframes)
25:11 Start and end percent
CREDITS
=========================================================
🎵Music
Song: Bike Box, Artist: Kia, Music by: CreatorMix.com
✂️ Edited with Canva, and ClipChamp. I record the stuff in powerpoint.
========================================================
© 2024 Koala Nation
#comfyui #animatediff #stablediffusion - Věda a technologie
I'm just finding this now it's helped so much with my videos thank you so much
I love you liked it!
Hey man i just went into SD like 3 days ago, i was struggling to find someone who really knows how to explain all this animation novel, after watch more than 10 videos i can easily say: you a are a great teacher and the best out there. Thank you very much! I wish you can stay posting all this valuable content, i will keep watching and hitting like! cya!
Thanks! Good luck in your SD journey!
amazing level of detail in this guide. thank you greatly this cleared up a lot of confusing things
You are welcome! Truth is that using AnimateDiff can be pretty straightforward after you use it for a while, with more or less complicated workflows. However, it has quite a lot of options and possibilities. The github explains it, but I find out is better to show some practical examples. I love you liked it!
what youre doing is absolutely amazing, thank you very much. i appreciate it a lot
do you maybe have a discord?:)
Hi! I do not really have time for it...working in the workflows and the videos already take most of my free time, which is not much...
@@koalanation okay I understand.. I would love to talk with you from time to time:) you are very knowledgeable, I have a project I’m working on and I could tell you about it and maybe you have some ideas on how to improve it and maybe it inspires you to do something similar. I think there is good money in it:)
Hello, thank you very much for the content you create, it is very valuable :).
There is a node that you use in your workflow, which does not work is the COCO-SemPreprocessor. Which one could you replace it with?
You can use for example ultralytics detector with Sam detector from the impacts pack, or for this case It will be easier if you do it by hand using the mask editor (right click over the image and that option should appear)
Quite impressive. It would be great if you could provide the various stages of the workflow. I'd be happy to become a Patron, for example.
Thanks! I have uploaded some of the examples in my civit.ai page for the AD guide: tinyurl.com/6649xxpn. There you can download the zip file with the Part 1 examples. There are some of the workflows that are made during the video.
I'd love to make a patreon, but that unfortunately will require too much time for me...anyway, any contribution to cover some of the costs of running the GPU rental would be great....check out some of the affiliate links I have in the description (if you plan to use those services), or a small ko-fi donation.
Thanks!
@@koalanation Thanks for your reply. I totally understand. Hopefully you'll find the time to create a Patreon and upload every step of your workflows and various experiments.
Welcome Stable Diffusion 3 :)
Let's see when they SD releases the weights, and later when can be implemented for AD....that would be great!