Aitrepreneur
patreon
1-Click INSTALL VACE VIDEO CONTROLNET IMAGE TO VIDEO ComfyUI WebUI!
🕑 Added 2025-05-22 17:24:59 +0000 UTCHey everyone! I've created a 1-click installer for the newest "THE NEW AI VIDEO CONTROLNET KING! ", called "VACE". Simply THE MOST POWERFUL UPGRADE TO AI VIDEO GENERATION EVER! A ControlNet-style adapter for WAN 2.1 that gives you perfect control over your video generations using OpenPose, Depth, Segmentation AND WHEN Paired with the special LoRA CausVid, you can now generate videos up to 4x faster than beforeโฆ It's just amazing!
You can check out the video right here: https://youtu.be/zhNKpdL03PA
The workflow: VACE VIDEO CONTROLNET IMAGE TO VIDEO WORKFLOW! | Patreon
The installer of course automates the entire install process for comfyUI and the models downloads!
LOCAL INSTALL!!! RECOMMENDED TO START FROM SCRATCH SINCE YOU NEED THE LATEST COMFYUI TORCH VERSION!!!
1. Download the VACE-COMFYUI-MANAGER_AUTO_INSTALL.bat
2. Run the bat file and select either option 1, 2 or 3 depending on your GPU vram
3. Wait for the install to finish
4. The webui will launch, load the VACE_IMAGE-TO-VIDEO_CONTROLNET.json file and there you go๐
IF YOU ALREADY HAVE COMFYUI INSTALLED USING A PREVIOUS INSTALLER:
1. Download the VACE-MODELS-NODES_INSTALL.bat and place it in the ComfyUI_windows_portable\ComfyUI folder
2. Run the bat file and select either option 1, 2 or 3 depending on your GPU vram
3. Wait for the install to finish
4. ???
5. Profit ๐
IF YOU ARE USING RUNPOD:
1. Create an account if you haven't already: Runpod
2. Click on Pod (on the left side) then click deploy
3. Choose a GPU with at least 24gb of VRAM (a cheap 3090, 4090 or an A30 are great), click here for the comfyui template (aitrepreneur/comfyui), then edit the template and choose 80gb for both the container and volume disk, then deploy on demand
4. Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 8888"
5. Then go inside the comfyui folder and then drag and drop the HIDREAM_AUTO_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI
6. Copy and paste these two lines then press enter:
chmod +x VACE_AUTO_INSTALL-RUNPOD.sh
./VACE_AUTO_INSTALL-RUNPOD.sh
7. Wait for everything to be installed
8. Go back to the port 3000 and click on the manager to update comfyui and restart it
9. Load the VACE_IMAGE-TO-VIDEO_CONTROLNET.json file and there you go๐
Also use the command: tail -f comfyui.log
inside the workspace/logs to get the real time logs so that you always know when the install is done, It will then ask you to restart, so click on that restart button, wait for the webui to reboot, click refresh once it's done and there you go.
IF YOU ARE USING RUNPOD AND YOU WANT TO STOP THE POD THEN RESTART IT:
1. Go inside your pod
2. SERVICE port 8888
3. Go inside the Comfyui folder, open a terminal icon and re copy and paste those two lines:
chmod +x VACE_AUTO_INSTALL-RUNPOD.sh
./VACE_AUTO_INSTALL-RUNPOD.sh
4. And then in a few seconds it will reinstall all the requirements for the nodes
5. Go back to comfyui port 3000, click on manager, click update all, wait for everything to be updated then restart.
6. Re drag and drop the VACE_IMAGE-TO-VIDEO_CONTROLNET.json file inside and there you go๐
As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun๐!
Comments
Aitrepreneur
that is a lack of vram, what are you parameters here?
Dr. Brian Burton
I am getting the error VHS_LoadVideo cannot allocate array memory. Any suggestions on where to start troubleshooting?
Aitrepreneur
install git for windows
Madhy Odreman
Runing the COMFYUI for the first time and I am getting the following error: Cannot start or run due to compatibility with 64-bit version of Windows. Please contact the software vendor to ask if a 64-bit Windows compatible version is available.
Aitrepreneur
send me some screenshots of the parameters before and after the generation
StatusGear
I got the error : 'SymmetricPatchifier' object has no attribute 'get_grid' . I assume it has to do with not having get_grid probably from some nodes. I do have comyfui_controlnet_aux (60 conflicts) , comfyUI-GGUF (2 conflicts) , and ComfyUI-KJNodes (2 conflicts). But I just want to reconfirm.
Jayson King
Can anyone give me suggestions for improving the faces of people at a mid to far distance within this workflow? i get good results if im close up like the demo but as soon as i run this on people mid to far, the faces are smudged. i was considering trying face swapping. ive upped the steps and even tried the cause vid v2... but im a noob so need some real expert advice.
Frank B
OT: Any chance of an All in one install and Comfy work flow for the newly released flux kontext? been using it in flux playground and its pretty damn amazing.
Boy Thee
that's saying that the model did not download completely. so download the model manually and place it in \DWPose the other dirs are install trash
jonnylpg1993
DWPreprocessor [Errno 2] No such file or directory: 'D:\\Program Files\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\yzd-v\\DWPose\\.cache\\huggingface\\download\\0XR-wYEaL4qLqwIO4oYox_j1wmI=.7860ae79de6c89a3c1eb72ae9a2756c0ccfbe04b7791bb5880afabd97855a411.incomplete' Does anyone have a solution or where to download and place the file to make it work?
Ruti Bindehassan Gayle
I need your help, overlord. I have followed the instructions and the console stops at "press any key to continue" they closes and won't launch.
Dustin Lausch
To be safe I always use Conda to create an ENV and then activate it, run the .bat files from inside the ENV and it seems to keep things safe outside that shell.
Gimmy Grayn
Got same error on Win10 64-bit
Martin Markoviฤ
I assume this does not create virtual environment and can fuk up my current python ?
Anthony
New PC, windows 11. I get a error a The program or feature "\??\E:\git-setup.exe" cannot start or run due to incompatibity with 64-bit versions of Windows. Please contact the software vendor to ask if a 64-bit Windows compatible version is available.
simon myers
I get this error when I try to make a video, same thing happens when any of the control nets are used. I've checked the file path and nothing is there. I've updated comfy ui and checked for missing nodes, but it shows nothing is missing. Any ideas? edit- I can run text and image to video wan just fine. I installed using your installer - VACE-COMFYUI-MANAGER_AUTO_INSTALL DWPreprocessor [Errno 2] No such file or directory: 'C:\\Users\\xxxx\\OneDrive\\Documents\\_PROJECTS\\_AI_ART\\COMFYUI\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\yzd-v\\DWPose\\.cache\\huggingface\\download\\0XR-wYEaL4qLqwIO4oYox_j1wmI=.7860ae79de6c89a3c1eb72ae9a2756c0ccfbe04b7791bb5880afabd97855a411.incomplete'
Aitrepreneur
use a resolution that a multiple of 8/64. I like using 720x720 for a square and 720x480 for vertical/horizontal
Fredden
Hi! I get this error: The size of tensor a (15276) must match the size of tensor b (15504) at non-singleton dimension 1
Russ Ader
I have no idea how you are getting this to work in a couple minutes, even with a RTX 4090 and the larger model. I have downgraded all the way down to the Q3 version and it is still taking me over 20 minutes to generate a few seconds. I have an RTX 4070 TI Super (16 gigs vram) and this is slow as snot. Even with the Q3 model my vram and GPU are completely maxed out. EDIT: Just looked again, it's at 20 minutes and says it will take another 10 minutes to finish. Thats over 30 minutes with a Q3 model.
Cha
Hello, two custom nodes are not appearing in ComfyUI, namely WanVaceToVideo and TrimVideoLaten
Aitrepreneur
this means that you are not selecting your downloaded model in the first node
relaxama
* LoaderGGUF 21: - Value not in list: gguf_name: 'Wan2.1-VACE-14B-Q4_K_S.gguf' not in ['Wan2.1-VACE-14B-Q8_0.gguf'] Output will be ignored Prompt executed in 3.44 seconds got prompt Failed to validate prompt for output 8: * LoaderGGUF 21: - Value not in list: gguf_name: 'Wan2.1-VACE-14B-Q4_K_S.gguf' not in ['Wan2.1-VACE-14B-Q8_0.gguf'] Output will be ignored Prompt executed in 0.06 seconds if its liek this do i run again the model noeds install bat?
Nicolas Diaz
Hey there just wanted to point out there was likely an error in your runpod instructions. You have us dragging over the HiDream.bat file then inputting into terminal the run command for VACE. I am a newbie so I somehow thought HiDream needed to be installed to run VACE because of this.
Gabbis85
To clarify i did get an error starting the rendering so i did turn this error off: DepthAnythingV2Preprocessor Fast download using 'hf_transfer' is enabled (HF_HUB_ENABLE_HF_TRANSFER=1) but 'hf_transfer' package is not available in your environment. Try `pip install hf_transfer`. fix was to edit the file: "run_nvidia_gpu.bat" to this: set HF_HUB_ENABLE_HF_TRANSFER=0 .\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build pause to clarify i did turn this off and it worked fine i think, can atleast make clips, but do i really need HF_TRANSFER? anyone else has this off? i did ofc try manually install hf_transfer, but did not work for me
