Video

Great to hear! <3

Yes, I am try to improve it. Thank you <3

The light map should also have same number of frames or greater than the source video. Example 1 Source Video = 5 seconds Light Map video = 1 second Result : Error - The size of tensor a (20) must match the size of tensor b (10) at non-singleton dimension 0" Example 2 Source Video = 5 seconds Light Map video = 5 second Result : Successful Render Hope this make it clear

@@jerrydavos I am using the source file you provided. helenpeng.mp4 and LightMap.mp4 The two are equal to 20 seconds. Do I need to set frame_load_cap? To zero?

Yes, it's a sort of bug, I also face it sometimes ... What you can do is first reload the page and then spam the Ok button of the error dialogue box till it disappears. Reload page again and spam ... mostly 2-3 time it will work Else you can install the nodes manually here: 1. github.com/daxcay/ComfyUI-JDCN.git 2. github.com/bronkula/comfyui-fitsize.git 3. github.com/ltdrdata/ComfyUI-Impact-Pack.git 4. github.com/kijai/ComfyUI-KJNodes.git 5. github.com/mcmonkeyprojects/sd-dynamic-thresholding.git 6. github.com/cubiq/ComfyUI_essentials.git 7. github.com/giriss/comfy-image-saver.git 8. github.com/M1kep/ComfyLiterals.git 9. github.com/theUpsider/ComfyUI-Logic.git 10. github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git 11. github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved.git 12. github.com/Kosinkadink/ComfyUI-Advanced-ControlNet.git 13. github.com/shiimizu/ComfyUI_smZNodes.git 14. github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes.git 15. github.com/Nourepide/ComfyUI-Allor.git 16. github.com/WASasquatch/was-node-suite-comfyui.git 17. github.com/Fannovel16/ComfyUI-Video-Matting.git 18. github.com/Fannovel16/comfyui_controlnet_aux.git 19. github.com/comfyanonymous/ComfyUI_experiments.git

Thank you!

Yes, OpenPose is the name of the Colorful Noodles

@@jerrydavos Thanks for your response. Have you created any video tutorial on that?

@@MOTIvaTIoN-wh8qy First 2.5 mins of the above video is the steps on how to extract OpenPose.

Yes, It is capped to 12 frames as default... so The user may not render all frames mistakenly and freeze their computer.

@@jerrydavos i guess its still isnt possible to do remastered 1-2 hour full length video with one click? been trying to find this workflow for a while

@@kilikilio5321Unfortunately no, the consumer GPUs we are using are not capable yet to hold 1-2 hours of data in Ram and run in just one click It is still Possible but very tedious with the above workflow... using the Vid2Img or Img2Img workflow and rendering in short batches and combining all the frames when done. But it's a huge headache for 1-2 hour long. You can research on Topaz Video AI Enhancer in that case, maybe it can do long renders.

I used my Background changer workflow and added a snow landscape image in the background. Workflow Reference: www.patreon.com/posts/v4-0-background-104651162

Around 8 GB GPU Vram for 50-60 frames is needed minimum. Disk Size required is also 6-8GB... around same.

it can be made using simple shapes and animating with after effects. Else you can search more "Contrasting" geometric pattern animation videos on stock websites, like shutterstock, gettimages, pexels, pixabay etc... Also I've included some samples light maps already in the workflow link folder here: drive.google.com/drive/folders/1bFfBs8mkN1HLtT1Xy6wsuOV4jl2WqiO4

Yes, I am experimenting on changing cloths and still preserving the motion of the character. Thanks!

Set the frame_load_cap from 10 to 0 inn the load source video node to render all frames

😂😂

Yes It's made in comfyui

@@jerrydavos I have your workflow , nice! Goodjob 👍🏼 Soon with Sdxl ?

Yes, Please recreate the save image node at the end and connect the lines like before.

Hey, You have to follow the video from 7:43 to extract frames. If still you are facing ram issues while extracting the passes, then you can use the passes exporter workflow from here: drive.google.com/drive/folders/1hLU5MhikUe6SnEnEPQc3tKTaNGmFT6p2 and how it works is here: www.patreon.com/posts/v4-0-controlnet-98846295 Extract the passes you need for IC light batch workflow, which is depth, mask and frames. Then Follow as normal in the video from 11:00

😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊😊

You can Ignore the "OpenPose Groups" and 1) Connect the line art pre-processor with the images (with a load image node or so..) you want as inputs to the controlnet node Input "image" 2) Change the load controlnet model to lineArt as well Just play around with strength and end percent till you get your results.

FaceFix don't change the scene much... you can try changing the "Depth" controlnet model and it's processing node to LineArt Controlnet Model and Lineart Preprocessor .... and play with the strength and end percent, maybe it can help your situation.

Hey, Sorry if I missed out the manager... Download it from here: github.com/ltdrdata/ComfyUI-Manager and Put it in ComfyUI > Custom nodes

@@jerrydavos Work Thanks

Yes, you can. Just copy and paste your folder path where you want to save the video or the images.