Native Wan VACE - Long Video Gen (Unlimited Length) - Version 20250708
Added 2025-07-07 19:31:09 +0000 UTCLast time, I posted the Long length video V2V gen., based on some math and indexing point to gen each chuck of video. https://www.patreon.com/posts/comfyui-wan-2-1-133333679
From the long freaking list of groups after groups... workflow. In programming, it's like hard coding a software conditions...
And I throw that garbage out and recreate the extension part.
I cut all those extra stuff, but the good thing is....
Now , we are all able to generate as long as you want. And no limited to how many samplers , groups, whatever shit that is.
Thank you @Usako_USA in Youtube who asked me this , and I was thinking, yes, there should be some Custom Nodes for Looping in ComfyUI? Tech background people built this tool, there should have something like this , just like in programming!
I sit down shut my door, no interruption. And I find what I need in ComfyUI Easy Use node pack.
I don't know why in Youtube or any place that I learn Comfyui before, no one have teaching this, and the IF statement.
These nodes should be the fundamental stuff for a node base software like a programming logic apply into workflow!!!
So right now, everyone , no more Video Index Out Of Range error message, if you didn't know how to calculate those frame numbers game. Or after 3, 4, 5, 6, sampling groups, how can I extend more.... etc..
None of it happen anymore! Cause I did the math here.
And now it's dynamic based on how many extend length you have, it will loop how many times.
I decide to roll out this version for all people. Patreon supporters, people who followed here. who cares, just use it!
gogogo!!!
update: (2025-07-08) img2vid workflow added here.
Comments
Hey! Great workflows. Love your work. v2v worked perfect for me. Now when using i2v. It seems like it's not working with the reference image and giving me a prompt base output only. I'm using the Wan2.1_T2V_14B_FusionX_Vace-Q8.gguf just like you. Haven't modified the workflow at all. Any ideas what might be happening? Thanks!!
Franco Aiello
2025-09-10 05:12:02 +0000 UTCYou need something like iClone then. Yes , open source Controlnet is like a toy grade. When you go for more detail like cg movie, that is another level
Benjamin Law
2025-08-12 23:33:37 +0000 UTCI feel like the controlnet nodes that we use in our workflows are pretty basic (I also use these nodes thanks to your idea). I would like to find a way to be able, not only to replicate movements but also replicate much more detailed expressions. Sometimes I get the eyes look at somewhere in a weird way, or get non-human gestures, etc. I am looking for a more advanced controlnet technique or whatever it's called
Pedoneit
2025-08-12 19:47:15 +0000 UTCThe long video Gen works perfectly (i did one with 11 parts) but this one with loop does not work, after the first video part there is a big glitch and the video result after that is ugly
hf21
2025-08-11 09:42:36 +0000 UTCIts normal, because the overlap frames are coming from the previous batch. If you use it in the sitiching, your final video will get weird. Btw, 20 is too much. As I mentioned 6-10 is good enough
Benjamin Law
2025-08-07 14:25:23 +0000 UTCevery time I create a video and set the "Overlap frames" to 20, for example, I get a video in which these 20 frames are cut after each iteration.
Кьюбит Шоу
2025-08-07 13:51:55 +0000 UTCIf I join-up is there any kind of faceswap vid2vid you can show me??
AARON SOF
2025-08-05 20:51:12 +0000 UTCLength of the video missing in some part in your setting/ process
Benjamin Law
2025-08-03 07:29:12 +0000 UTChello. i am new to this. i saw your vid and downloaded the workflow. but i get this error when i try to run. the only change i made was the upscaler. i used the simple one since for some reason i couldn't install it properly. (Prompt execution failed TypeError: Cannot read properties of null (reading 'length')
Jim
2025-08-02 10:55:44 +0000 UTCI'm getting better results each time depending the lora combination, very impressive! There's something i don't underdstand though, on the far right of the workflow there're 2 nodes, the first "video combine" node that produces a video, and if i understand correctly, the final one at the end on the right that connects the upscale node and should produce the final, upscaled video. However i'm only getting a still image in that final "video combine" node, is that normal?
Vicente
2025-07-27 10:17:02 +0000 UTCI think this is your first workflow that works for me, almost all i had tried before gave me some form of OOM or other error. This one gave it too, but lowering resize_to HD instead of defeault 2k fixed it. Amazing tech here, 12 sec vid in 11min with great motion and okish image quality, which is probably related to the lora selection i have used which could be better, so i'll tweak some of this stuff now that this works. Overall amazing job, thanks a lot for this amazing piece of AI tech.
Vicente
2025-07-26 22:58:35 +0000 UTCSelf Forcing have 14B? Are you talking about LightX2V lora? If that so, that is just a change in the model and lora loader drop down. Doesn't need additional workflow change, if you really know what are you asking.
Benjamin Law
2025-07-17 08:00:00 +0000 UTCCan you add self-forcing 14B when you have time, and adapt the workflow to only sample once? That would be a great performance improvement.
2X
2025-07-17 07:54:48 +0000 UTCyou can DM me in here or Discord. Since, I have my own company running. I am pretty much busy most of the time, and doing AI content here for hobby. :) I have to check how many in the work load and what is the budget first.
Benjamin Law
2025-07-13 20:23:53 +0000 UTCProbably have to set up an offload as you go
DBJ19
2025-07-13 19:59:26 +0000 UTCHi Benji, is there a way to contact you directly? we are working on a project and might want to hire you to consult. Thank you!
DBJ19
2025-07-13 19:59:02 +0000 UTCThis has been really cool. It seems RAM ends up being the limiting factor. With a long video I eventually run out of ram and comfy crashes.
Nocare
2025-07-10 14:37:01 +0000 UTCyou mean yours?
Benjamin Law
2025-07-10 08:19:25 +0000 UTCall video outputs are blurred
Dominique B
2025-07-10 08:18:12 +0000 UTCthis is so good! thanks for all the math work behind!!! would like to ask, using the i2v workflow, does lora work for native Wan Vace? I experience lora key not loaded mainly like motion driven Lora. enhancement Lora (example: detailenhancement) sometimes loaded ok, and if there is the lora key not loaded error, i close and restart my comfyUI fresh then the error seems to go away. Most motion driven lora i use is for i2v, some t2v, using on kjwanvideowrapper is working fine. Model wise i use T2V or I2V model. i tried to test on VACE but due to Vace module and T2V model load separately in WanVideoWrapper, i get OOM once I add in Lora. Not sure what is causing it, maybe you can shine some light for me :D i am using this setup Wan2.1_T2V_14B_FusionX_VACE-Q6_K.gguf umt5_xxl_fp16.safetensors
Yih-Jia Tan
2025-07-09 09:06:45 +0000 UTCv2v have controlnet, and i2v just use the image, how can you have the same output?
Benjamin Law
2025-07-08 15:28:55 +0000 UTCHi. Could you please elaborate the difference between the v2v and i2v of yor latest iterations? The only difference I spotted id that v2v of them has prompt (which is completely ignored) and throws loopEnd exception after first batch of 81 frames (for the same input video/image as i2v)... The exception is: easy forLoopEnd '626.0.0.3.0.0.655'
Al Go
2025-07-08 15:24:06 +0000 UTCMight need to check your reference video size . Looks like after resize the mask are not the same res.
Benjamin Law
2025-07-08 14:57:38 +0000 UTCI get this error when I process a video thats 201 frames long and the frame length is 81: IndexError: The shape of the mask [81] at index 0 does not match the shape of the indexed tensor [49, 480, 832, 3] at index 0
PeterFuchs
2025-07-08 14:39:57 +0000 UTCWow much better. Thank you
Clayfacer
2025-07-08 13:18:58 +0000 UTC300+ fps?😱😱😱that is very very fast like 100M running speed, are you sure?
Benjamin Law
2025-07-08 12:20:58 +0000 UTCI am getting this issue The shape of the mask [81] at index 0 does not match the shape of the indexed tensor [37, 832, 480, 3] at index 0 my video is 300+ fps
Rahul Kumar
2025-07-08 12:18:43 +0000 UTCIts based on the video length now. You don't need to set. But its better the video is over 10 seconds let the beast run.
Benjamin Law
2025-07-08 11:36:41 +0000 UTCYou got an amazing piece of brain Benji. Thank you so much!
Rahul Kumar
2025-07-08 11:13:02 +0000 UTChow long is your video?
Benjamin Law
2025-07-08 05:27:21 +0000 UTChow do you set the # of loops, or the length of the video?
A Syed
2025-07-07 23:34:27 +0000 UTCThank you Benji. Constantly hitting "start index is out of range" from "Get Image or Mask Range From Batch" node (one, connected to the "DWPose Estimator")... it calculates start index as 152, while num_frames is 81... any suggestion?
Al Go
2025-07-07 22:29:57 +0000 UTCBenji, you are truly amazing ma man. Thanks a lot.
Lionel Vinuales
2025-07-07 22:13:13 +0000 UTCHaha thanks, you can try this one rather than the last version. but just be careful, summer time, have a extra cooler blow that gpu. Lol cause when running this workflow, its hot. Eyes, it need close up shot and use the face detection (i forgot the name, so many AI..) And then combine with DWPose.
Benjamin Law
2025-07-07 21:23:15 +0000 UTCHey benji.. You are such a gem always comes with something exciting ❤️❤️. I'm also keep working on your last long length workflow it was working fucking good and I ma damn sure this one gonna boom the whole journey. I have a question can you do something with eyes moment this is something which isn't getting controlled. I have generated more than 20 videos on different settings and value but everything it gives robotic eyes moment. Can you look into? Because this is something I'm not able to control and it's obviously differentiate between real video and AI generated videos.
Temp Mail
2025-07-07 21:18:49 +0000 UTCI think this to be more dynamic way now. So we don't have to keep having so much nodes... Make me dizzy lol
Benjamin Law
2025-07-07 21:10:28 +0000 UTCThis looks incredible. I want to see how this works later on when I can try it. This is how you move things forward. Great work. I have been working on a V2V custom temporal fix for Wan 2.1. it's a very meticulous set up but it produces really good results with Low Quality videos. I'm still working on it but I am very happy with how it's turning out.
Intellectz Productions
2025-07-07 20:57:28 +0000 UTCUse this gen movement and bring to the v2v mutlitalk that I posted previously, and its done.
Benjamin Law
2025-07-07 20:32:47 +0000 UTCThis update I solved it, and run few video, using color match it fix. If I use Self Forcing 1.3b.... yes it works without change all workflow structures, just change the model. It is consistent, but the quality is very low. So I haven't use self forcing 1.3b after all.
Benjamin Law
2025-07-07 20:26:49 +0000 UTCCan i use this workflow to give body movements to a lip synced video?
AiInfluence
2025-07-07 20:21:07 +0000 UTCI got very close to solving color shift by sending in my reference image alongside all my FFLF controlnet frames and masks. I’ll probably make a video about it - you just need to manually trim the first 4 frames of the output - Trim Latents node makes for ugly start frames
Hayden Martin
2025-07-07 20:05:53 +0000 UTCHave we solved color shift yet?
Hayden Martin
2025-07-07 20:05:07 +0000 UTCyou rock man I truly admire this
Daniel Aparecido
2025-07-07 20:00:57 +0000 UTCvery smart, very cool
Ricky Possum
2025-07-07 19:51:34 +0000 UTCOMG thank you Benji, you best.
snehanshu badaik
2025-07-07 19:39:16 +0000 UTC
