![Koala Nation](/img/default-banner.jpg)
- 29
- 132 105
Koala Nation
Netherlands
เข้าร่วมเมื่อ 5 ส.ค. 2022
Check my ko-fi ☕ and support the channel: tinyurl.com/mw9byj6r
Welcome to my TH-cam channel dedicated to Stable Diffusion, ComfyUI and AnimateDiff tutorials, animations, and more!
In the channel you will find tutorials that will help you unlock the full potential of Stable Diffusion. Whether you’re a beginner or an expert, we’ve got you covered with step-by-step guides, insightful tips, and tricks that will take your AI video generation skills to the next level.
Get ready. Embark on an amazing journey as we explore Stable Diffusion and ComfyUI. Our videos showcase tutorial with this cutting-edge technology, providing inspiration for your own projects.
Thank you for choosing KoalaNation as your go-to resource for ComfyUI, AnimateDiff and Stable Diffusion, Let’s do it together!
Welcome to my TH-cam channel dedicated to Stable Diffusion, ComfyUI and AnimateDiff tutorials, animations, and more!
In the channel you will find tutorials that will help you unlock the full potential of Stable Diffusion. Whether you’re a beginner or an expert, we’ve got you covered with step-by-step guides, insightful tips, and tricks that will take your AI video generation skills to the next level.
Get ready. Embark on an amazing journey as we explore Stable Diffusion and ComfyUI. Our videos showcase tutorial with this cutting-edge technology, providing inspiration for your own projects.
Thank you for choosing KoalaNation as your go-to resource for ComfyUI, AnimateDiff and Stable Diffusion, Let’s do it together!
LivePortrait - Animate faces and create avatars with ComfyUI #comfyui #stablediffusion
Animate faces using LivePortrait in ComfyUI. Create new compositions of your images or videos, using reference videos to express with the mouth and the eyes. Create talking avatars using this custom nodes and workflow using ComfyUI. No AnimateDiff needed this time!
Unleash the power of Stable Diffusion with ComfyUI and AnimateDiff.
💻 Kijai LivePortrait: tinyurl.com/yc788zby
💻 ShadowCZ007 LivePortrait: tinyurl.com/y6bax7uc
📡 Official implementation: github.com/KwaiVGI/LivePortrait
🕸️ Discord: discord.gg/UaFQkfYgAQ
Git for windows: tinyurl.com/2jz3rxp5
#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
============================================================
CREDITS
===========================================================
Disloyal man walking with his girlfriend and looking amazed at another seductive girl by Antonio Guillem:
tinyurl.com/mr3x4ezp
🎵Music
Song: Bike Box, Artist: Kia, Music by: CreatorMix.com
It's Our Time, Music by CreatorMix.com
✂️ Edited with Canva, and ClipChamp. I record the stuff in powerpoint.
========================================================
© 2024 Koala Nation
#comfyui #animatediff #stablediffusion
Unleash the power of Stable Diffusion with ComfyUI and AnimateDiff.
💻 Kijai LivePortrait: tinyurl.com/yc788zby
💻 ShadowCZ007 LivePortrait: tinyurl.com/y6bax7uc
📡 Official implementation: github.com/KwaiVGI/LivePortrait
🕸️ Discord: discord.gg/UaFQkfYgAQ
Git for windows: tinyurl.com/2jz3rxp5
#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
============================================================
CREDITS
===========================================================
Disloyal man walking with his girlfriend and looking amazed at another seductive girl by Antonio Guillem:
tinyurl.com/mr3x4ezp
🎵Music
Song: Bike Box, Artist: Kia, Music by: CreatorMix.com
It's Our Time, Music by CreatorMix.com
✂️ Edited with Canva, and ClipChamp. I record the stuff in powerpoint.
========================================================
© 2024 Koala Nation
#comfyui #animatediff #stablediffusion
มุมมอง: 432
วีดีโอ
Audioreactive AnimateDiff video clips with ComfyUI (AI Music Videos) #comfyui
มุมมอง 1.6K14 วันที่ผ่านมา
Create unbelievable visuals for music videos using this audio reactive workflow for ComfyUI and AnimateDiff. Using the audio nodes from SaltAI, masks can react to different audio frequencies following the rythm of the music. In combination with IP Adapter and AnimateDiff, exciting video clips and compositions can be made. Unleash the power of Stable Diffusion with ComfyUI and AnimateDiff. You c...
Inpainting AnimateDiff DINO (ComfyUI animation workflow) #stablediffusion #comfyui
มุมมอง 2Kหลายเดือนก่อน
Amazing control of your animations using masks with the the Magic trio: AnimateDiff, IP Adapter and ControlNet. Explore the use of masks to texturize objects and create fantastic videos. 🔥 Complete workflow with extras (package) tinyurl.com/46pj8tpu Support the channel and have also (beta) access to the discord with demo runnable workflows! 💻 AnimateLCM: tinyurl.com/y43bjhee 🕸️ Discord: discord...
Easy Image to Video with AnimateDiff (in ComfyUI) #stablediffusion #comfyui #animatediff
มุมมอง 14K2 หลายเดือนก่อน
Easily add some life to pictures and images with this Tutorial. The Magic trio: AnimateDiff, IP Adapter and ControlNet. Explore the use of CN Tile and Sparse Control Scriblle, using AnimateLCM for fast generation. 💻 AnimateLCM: tinyurl.com/y43bjhee 🕸️ Discord: discord.gg/UaFQkfYgAQ #animatediff #comfyui #stablediffusion 💪 Support this channel with a Super Thanks or a ko-fi! ko-fi.com/koalanatio...
ComfyUI AnimateDiff Guide Part 2 - Tutorial #stablediffusion #comfyui #animatediff
มุมมอง 2.2K2 หลายเดือนก่อน
Second video of the 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 🖥️ Civit.Ai AnimateDiff parts 1 and 2: t.ly/07HuQ 🕸️ Discord: discord.gg/UaFQkfYgAQ #animatediff #comfyui #stablediffusion 💪 Support this channel with a Super Thanks or a ko-fi! ko-...
ComfyUI AnimateDiff Part 1 - Tutorial #stablediffusion #comfyui #animatediff
มุมมอง 3.8K3 หลายเดือนก่อน
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.gg/UaFQkfYgAQ #animatediff #comfyui #stablediffusion 💪 Support this channel with a Super Thanks or a ko...
AI 3D animation: convert your favourite 2D cartoons with AnimateDiff in ComfyUI #stablediffusion
มุมมอง 1.1K3 หลายเดือนก่อน
In this workflow we show you the possibilities of using RAVE to convert 2D cartoons into 3D looking style animations. Using ComfyUI and AnimateDiff, in combination with the RAVE sampler and denoising, it is possible to transform a complete 2D sequence and achieve great 3D consistency. Best way to do comfyui video to animation in 3D. This is not a comfyui 3D render, as there is not 3D mesh creat...
NEW UPSCALING method ComfyUI with 2 samplers AnimateDiff v3 + AnimateLCM
มุมมอง 4.1K4 หลายเดือนก่อน
NEW UPSCALING method ComfyUI with 2 samplers AnimateDiff v3 AnimateLCM
ComfyUI: RAVE for video transformation (vid2 vid) #animatediff
มุมมอง 6K6 หลายเดือนก่อน
ComfyUI: RAVE for video transformation (vid2 vid) #animatediff
Stable Diffusion Interpolation Comfyui vid2vid Tutorial IPAdapter ControlNet
มุมมอง 2.9K7 หลายเดือนก่อน
Stable Diffusion Interpolation Comfyui vid2vid Tutorial IPAdapter ControlNet
LCM + AnimateDiff High Definition (ComfyUI) - Turbo generation with high quality
มุมมอง 9K7 หลายเดือนก่อน
LCM AnimateDiff High Definition (ComfyUI) - Turbo generation with high quality
Animatediff perfect scenes. Any background with conditional masking. ComfyUI Animation
มุมมอง 9K8 หลายเดือนก่อน
Animatediff perfect scenes. Any background with conditional masking. ComfyUI Animation
AnimateDiff + Instant Lora: ultimate method for video animations ComfyUI (img2img, vid2vid, txt2vid)
มุมมอง 35K8 หลายเดือนก่อน
AnimateDiff Instant Lora: ultimate method for video animations ComfyUI (img2img, vid2vid, txt2vid)
ComfyUI animation with segmentation: TrackAnything with SAM models
มุมมอง 9K9 หลายเดือนก่อน
ComfyUI animation with segmentation: TrackAnything with SAM models
TrackAnything - ComfyUI Segmentation (with ControlNet, TemporalNet and masks)
มุมมอง 2.9K9 หลายเดือนก่อน
TrackAnything - ComfyUI Segmentation (with ControlNet, TemporalNet and masks)
Stable Diffusion ComfyUI Animations - Easy with ControlNet and TemporalNet
มุมมอง 15K10 หลายเดือนก่อน
Stable Diffusion ComfyUI Animations - Easy with ControlNet and TemporalNet
ComfyUI - Vast.ai: tutorial - how to rent cheap high VRAM GPUs for your AI art
มุมมอง 6K10 หลายเดือนก่อน
ComfyUI - Vast.ai: tutorial - how to rent cheap high VRAM GPUs for your AI art
ComfyUI ControlNet animation (with TemporalNet) - Stable Diffusion
มุมมอง 3.3K11 หลายเดือนก่อน
ComfyUI ControlNet animation (with TemporalNet) - Stable Diffusion
Daft Punk - Technologic (Remix) Melodic Techno videoclip cyberpunk
มุมมอง 991ปีที่แล้ว
Daft Punk - Technologic (Remix) Melodic Techno videoclip cyberpunk
Thanks! Can you release the workflow for video to video? 🙏
where do i save teh animate lcm model to?
hello, im wondering where the link is for the mask video?
You can download: ko-fi.com/s/7d5e1802f1 Use 0 if you want download it for free
@@koalanation thank you ! it will repeat on seamless loop? or its better without the loop?
@@visualdrip.official in the example the mask video is repeated several times so it seems it is looping. But you can also choose to have a 'static' mask, or to have a different one without looping...do what you like!
@@koalanation thanks so much for sharing!
You do a great job of explaining things. Well done
I try
I was wondering how did you bring node number on the box ?
If you go to the Manager, on the left column you will see the option 'Badge'. There you can set the number of the node to appear over the node.
@@koalanation thank you !
Hi,thanks again iam very thankful. About the context options, is there any best combination to use for best output? Tbh I didn't understand d technical part. And I want to ask what do you recommend me to watch next, please :)
Hi! I normally used Standard Uniform or Looped Uniform. Depending on what you want to do, one may be working better than the other. You will need to experiment. Looped uniform works better for 'loops', at it blends last and first frames, but for general animations is also good. If you have not seen the first part of the series, look at th-cam.com/video/E_GnupiwAeY/w-d-xo.html A relatively simple workflow: Img2vid th-cam.com/video/yHMcsRZGMEo/w-d-xo.html If you want to do some character transformation, check out: th-cam.com/video/4826j---2LU/w-d-xo.html. This is complex, but I love the audio reactive workflow: th-cam.com/video/35H2VWbSQ08/w-d-xo.html
Error occurred when executing KSampler: 'NoneType' object has no attribute 'size'
how did you export masks generated by trackanything? did you rewrite some code or you can do that within its webui?
Yes, I made some changes in the code (with my limited programming skills, I managed to get it working like that): github.com/dsigmabcn/Track-Anything.git There are easier and better tools now integrated in ComfyUI. Check out: th-cam.com/video/5mHmDx4dWAM/w-d-xo.html
Amazing video tutorial, took two days to implement it and get it working now. Although still not quite understand some bits of it. Again, brilliant video, thank you so much!
@@liangmen Happy to hear you managed to get it working. It is not easy, definitely
Finally a detailed tutorial. Continue more like this video please
Thanks! There are not such deep dives, it is true...when I find some time I will do part 3
yeah, no to SD1.5 anything.
Did SD1.5 hurt your feelings?
only if i had a good system!
@@VaibhavShewale yep, it is heavy. The animation stuff at the end eats a lot of resources...
@@koalanation damn dude the hour of editing you have spent is just on next level
Well, yep! 😀😀😀 th-cam.com/video/y7VOBcrk7J8/w-d-xo.html
That is really cool!
pretty cool way to sync masks with audio and create a reactive music video. awesome.
Top! Love your videos!
😮 Thats awesome🙏. Will try it soon 😏
@@PixelsVerwisselaar good luck! Many cool things can be done with some imagination!
when I click Queue Prompt is says "TypeError: this is undefined" and nothing happen. I have all required nodes/models, and comfyui updated/restarted. can you please help?
Hi! I have never encountered this error...googling it refers to an issue with MixLab nodes...not sure if that would be your case. Maybe try to disable or uninstall custom nodes to see if there is one affecting ComfyUI.
best videos thank you. great teacher
Love you enjoy it!
I'm just finding this now it's helped so much with my videos thank you so much
This did wonders
@@xr3kTx it is fun!
@@koalanation I took great inspiration from your workflow because I need to understand the tools at play, I actually did this with SDXL. I am using a framecap of 100, however the face seems to glitch. Can you suggest anything for the face glitching? I did use ipadapter with style and composition transfer, but every few frames it seems to redo the context.
@@xr3kTx I did not dare to use SDXL because of the GPU and VRAM requirements...besides, SDXL AnimateDiff is also difficult...with hotshot is ok, but then you are limited in a context window of 8 frames...not sure if testing with SD 1.5 is an option for you. You can always upscale and refine the output
@@koalanation I have had better results with SDXL personally (I am using a lora and sdxl respects it more for my character + ip adapter for style), I am using RTX A6000 on runpod so resources are less of a concern, its the workflow that I need to improve.
@@xr3kTx good to know. I may then give it another try...have you tried with free init in AD? Not sure how it will work with this setup, though. But it is a lot of trial and error, you know...
thank you for your video, that's very helpful
Love your videos so much! Can you make a tutorial video on FlexClip’s AI tools? Really looking forward to that!
Thanks for the idea!
hey i'm getting this error "Could not allocate tensor with 828375040 bytes. There is not enough GPU video memory available!" I have an AMD Rx6800Xt 16gb vram, any workaround or fix? Thanks
Hey! Not sure what the messages are with AMD, but maybe you can try first reducing the size of the latents and/or reducing the batch size. Looks like some limitation with the VRAM.
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)
Thans for the tutorial! Question: Is it possible to feed Comfy with a reference video for it to animate the image using said video as reference? Like, say I have an image of a character, and I give Comfy a video of someone skateboarding, is there a method with which I could get comfy to animate the character skateboarding based on the video? Cheers and thanks in advance!
Yes! You can use a reference video and use controlnets such as openpose, depth, lineart, etc, to guide the composition of each frame. There are many videos and tutorials about it.
@@koalanation Thanks for replying! The most I've been able to find are tutorials on animating a referenced image using prompts or generating a video using another video as reference also using prompts, have yet to find one where they animate a reference image based on a reference video, guess I just have to look harder tho!
Check out: th-cam.com/video/XO5eNJ1X2rI/w-d-xo.html. Take into account this is rather complex with all the samplers and so on. Here: th-cam.com/video/Ka4ENd63VBo/w-d-xo.html, I think it is more clear, but take into account the IP Adapter node it does not work like in the video anymore.
Great video! I'm new to all that and im wondering of there is a way to keep the details. I'm trying to use a city skyline as img to video, and there for example, a lot of windows are getting removed.
That seems difficult with this method If the windows are small. Reducing the scale factor may work. Otherwise some trick with masks and controlnets may work but I have not really tried it with sparsectrl
Thank you :) I got it working with the pytorch version!
Excellent! Have fun
@@koalanation short catch-up -> used it multiple times now + adapted your script and it works like a charm. Thank you very much for the video, as without it I would either have spended way more time setting it up or even have given it up before getting it to work.
@@TheFusssi good to hear!
I'm getting an error with IPAdapterUnifiedLoader, says clipvision model not found. I've downloaded a few versions and put them in my clip_vision folder but still getting the error. Is there a specific one for this node?
Sometimes with IP adapter is confusing...try to use the IP adapter model and clipvision separately (without using the unified loader) following the instructions of the IP adapter repo. I like plus and VIT-G. github.com/cubiq/ComfyUI_IPAdapter_plus?tab=readme-ov-file
I love you liked it!
"easy"
🤣🤣🤣
I couldn't make it work :( I get this error every time: Error occurred when executing ADE_ApplyAnimateDiffModel: 'MotionModelPatcher' object has no attribute 'model_keys'
Seems odd...are you using AnimateLCM_t2v? Maybe try with other model to see if it runs, or use the gen 1 AnimateDiff Loader
I have the same
Use the model at: civitai.com/models/452153/animatelcm and make sure nodes and comfy is up to date.
@@koalanation oh... i wrote solution here but i dont know why is it not added... so... in my situation, there was problem when i was updating AnimateDiff from Manager. To fix it remove AnimateDiff from custom nodes and get AnimateDiff from repo, then place it in Custom nodes - works for me
Ok! I have not see it neither...anyway, sometimes during updates this things happen
Thanks for this, easy to follow and full of information!.. Love it!
great video you skipped some steps but still detailed. Question, do we not need to change the text prompt for each randomized pic > Also why did you use Load video path node for an image ?
Hi! In principle you do not need to change it, but you can, of course. Take into account the 'tile' control net is rather strong and you cannot do big transformations. The Load video node allows you to use http addresses, but the Image load node not (at least did not work for me). That is why I use it for the randomized image.
Geeez this takes long to run. which gpu do you have? amazing tutorial !!!
Hi! Thanks! I am using a RTX4090/3090 or A5000 via Runpod, which generates the video rather fast. You can try to decrease the number of frames and also the resolution of the images. Try to do interpolation with 3 frames instead of 2.
thanks. very useful tutorial.
Thanks for watching!
im back again , another great tutorial ...
Thanks mate!
So good! Would adding rave to this increase the consistency even further. Thanks
That sounds like a great idea! Take into account the VRAM requirements of RAVE, but apart from that, you could get something really cool combining these techniques!
@@koalanation cool ill try recreate this on a6000 card and add rave. Thanks!
Loved this. Thanks man
Thanks for watching!
very easy tutorial only took me HOURS to do it, I'm curious how to make people walk or move with comfyui.
Well, I cut quite a bit to show only the main steps, otherwise the video is mostly rendering... For moving people, controlNet with a reference video of someone walking is probably the way. With motion director should also be possible, I believe, but I need to find the time to try and see if results are 👍
It all worked and animates the image but every time it comes out very bright and faded. Any suggestion on how to fix it?
It appears the results in the tutorial are also faded and over brightened but at the end when you show examples they look fine. Did you find a fix or was it in your post processing?
Depending on the source of image, settings, etc, the image might be too dark or too bright, as you say. There are nodes that do that. I like Image Filter adjustments. But I think it is better to use a regular video editor, it is faster and easier to use.
Used Pytorch template and follow your instruction. After showing "To see the GUI go to: 0.0.0.0:3000", went back to the instance interface, click "Open", it opens another JuperLab ...
I have the same problem
I got it to work when I added "-p 3000:3000 -e OPEN_BUTTON_PORT=3000" to the docker options
@@leonardholter17 thanks man!
hey buddy , how did u copy second Ksampler with all lines connected duplicated ? at time line 4:40
Copy normally with ctrl+c, then paste with ctrl+shift+v.
@@koalanation ty my man
thx, ur videos helps :)
Great vid!
👍
hello! Does SparseControl work with AnimateDiff LCM properly? not V3?
Hi! With the V3 lora adapter works. I am not sure if that is the way it was intended, but it does something. I have tried to use the RGB sparse but I do not manage to get it work nicely...you can also switch to version 3 and fine tune results, but obviously generations will take longer
If you prefer it without the ai voice, check out with original voice (in Spanish) th-cam.com/video/GsOTnGeXCCg/w-d-xo.html
any toturoal for easy translation of voice offline using ai ?
Can you set up the whole thing for us to use it?
Yeah, that was really easy, piece of a cake 🤣
Yes, it was 🤣
Very cool and detailed tutorial! Wish there was a guide for advanced controlnet's weights too, thanks for your work!
Where would I add a custom trained lora? after the load checkpoint?
Yes