วีดีโอ

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!

I try

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! 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

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

@@liangmen Happy to hear you managed to get it working. It is not easy, definitely

Thanks! There are not such deep dives, it is true...when I find some time I will do part 3

Did SD1.5 hurt your feelings?

@@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

That is really cool!

Top! Love your videos!

@@PixelsVerwisselaar good luck! Many cool things can be done with some imagination!

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.

Love you enjoy it!

@@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...

Thanks for the idea!

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.

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)

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.

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

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!

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

🤣🤣🤣

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

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.

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 for watching!

Thanks mate!

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!

Thanks for watching!

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 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.

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!

Copy normally with ctrl+c, then paste with ctrl+shift+v.

@@koalanation ty my man

👍

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

any toturoal for easy translation of voice offline using ai ?

Yes, it was 🤣

Yes