v1.1 update:
Small update, adding Prompt Stash Saver and Prompt Stash Manager. Also fixed default resolution. Other minor fixes/additions, see About This Version for the rest.
I've also incuded the .json data for my prompt stash saver. This is a node that saves all of your prompts, which is an upgrade from copy/pasting them from the Notes in the workflow.
If you want to try and use my saved prompts, the file is uploaded here and goes in ComfyUI\custom_nodes\confyui-node-prompt-stash-saver
I don't even know if you can just put this file there or not, give it a try and let me know.
In the workflow I've been using it to store the prompts and I retrieve them and copy/paste but you can hook the node up directly and use it as input.
Edit:
Some of the LoRas that are present in this workflow (but aren't used) are no longer available on the site. Just an FYI for folks who are wondering https://civarchive.com/articles/13749
Edit 2:
I found out the default resolutions are a bit different than I originally thought, so the workflow is currently set for unoptimal resolutions (720x720 & 480x480)
14B Model I2V 720P - 1280x720 720x1280 768x76814B Model I2V 480P - 480x832 832x480 512x512The next version of this workflow will add some requested features as well as fix the resolution. For now you can change the dims in the WANImageToVideo node.
This is the workflow I use, I spent some time cleaning it up - keeping in mind other people would be using it. There are lots of notes with LoRa trigger words and prompts, and the current generation setup is a nice one ;)
Current prompt and loras setup to create a "dancing bear" type scenario where 2 gals are in the photo and along comes some guy that skeets on them. Then they kiss. Crazy how well it works. This is obviously extremely goonish so beware...
Many LoRas are referenced in the notes, but the two that are setup in the workflow are:
https://civarchive.com/models/1333275/passionate-kissing
https://civarchive.com/models/1350447/wan-cumshot?modelVersionId=1602715
Just grabbed a random AI generated pic of 2 chicks from Google and ran the prompt that's embedded in the workflow. This is the first generation that came out. You can expect to see a lot better.
720x720 in 153 secs on 4090.
The WAN Cumshot v1.1 LoRa is really good, it's set to .7 and that tends to keep char consistency well enough. If you give it a good pic you will get good results. This image is not a good pic but showcases the concept.
FROM WAN CUMSHOT:
To use with an image where no guy is present, you can either use
cum shoots from off screenor
A man enters the frame from the side. If her hand(s) off screen you can try
She is stroking his penis with {her hand | both hands}You can try:
"A woman / two women are sitting in front of a man / next to a man even when he's not pictured to cause him to show up.
Description
Fix default resolutions
Add Prompt Stash Manager and Prompt Stash Saver
Fix notes
Fix Bypass Switch (figured out how to filter stuff out)
Cleanup
FAQ
Comments (21)
Does it also work for t2v only?
I keep running into this error "UnetLoaderGGUF
GGUF magic invalid" I have no Idea what to do.
The error at the top says value 108, not sure if that even helps lol
Hi, I keep getting
ptxas` failed with error code 4294967295
Any clues on this error?
First time I've seen my own node, Prompt Stash Saver in the wild! ❤️❤️ Glad someone other than me is using it. I just added a new Passthrough node to make it easy to pause and edit prompts from LLMs. And yeah, if they drop that file in that folder, it'll work, but it'll replace any prompts they may have already saved. Maybe I could add an "import" on the manage node that will let people select or paste a json and it can merge it with the existing content if there's enough desire for it. Throw an issue on the git repo and see if anyone upvotes it, lol
Amazing work dude! If you have time please if you can do one for video extensions or add maybe a control/option. Your workflow is really simple and works amazing, not sure if you can do more optimizations with the latest nodes. Keep up the good work.
where do i download all the extra stuff it needs ?
google the missing models, google should help by pointing it to the sites.
I cannot get this to work on my 5090, will there be an update?
Thank you :)
Update:
This is the error: Is there a way to bypass it by any chance?
KSamplerAdvanced
CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
you need to download the latest Comfy build + update pytorch/etc for 5090 support. It's not the workflow.
try with pytorch 2.7.1 bcs u have cuda 12.8
try restarting comfy ui by closing the terminal. my be running out of memory.
I found it easier to work with a local repository not the comyui desktop app, pretty simple with powershell or VSCode and python. then u just run it in the browser and then install the app from there. Much easier to switch up and use your own venv. Then use git in your environment to make sure you have the right repositories. Took a little work but works like a charm.
For some reason WAN just crashes my ComfyUI on about 62-65%. 5070Ti BTW
I had this problem. Try a fresh reboot, and kill anything you don't have to run. Browsers, game clients, chat programs, Etc. This worked for me.
I'm going crazy..
Enyone how to fix this? i'm trying for hours but it wont work :/
Command '['D:\\ComfyUI_windows_portable\\python_embeded\\Lib\\site-packages\\triton\\runtime\\tcc\\tcc.exe', 'C:\\Users\\DARKEM~1\\AppData\\Local\\Temp\\tmp059ogzzu\\cuda_utils.c', '-O3', '-shared', '-Wno-psabi', '-o', 'C:\\Users\\DARKEM~1\\AppData\\Local\\Temp\\tmp059ogzzu\\cuda_utils.cp313-win_amd64.pyd', '-fPIC', '-D_Py_USE_GCC_BUILTIN_ATOMICS', '-lcuda', '-lpython313', '-LD:\\ComfyUI_windows_portable\\python_embeded\\Lib\\site-packages\\triton\\backends\\nvidia\\lib', '-LD:\\ComfyUI_windows_portable\\python_embeded\\Lib\\site-packages\\triton\\backends\\nvidia\\lib\\x64', '-LD:\\ComfyUI_windows_portable\\python_embeded\\libs', '-ID:\\ComfyUI_windows_portable\\python_embeded\\Lib\\site-packages\\triton\\backends\\nvidia\\include', '-ID:\\ComfyUI_windows_portable\\python_embeded\\Lib\\site-packages\\triton\\backends\\nvidia\\include', '-IC:\\Users\\DARKEM~1\\AppData\\Local\\Temp\\tmp059ogzzu', '-ID:\\ComfyUI_windows_portable\\python_embeded\\Include']' returned non-zero exit status 1.
I had a problem: KSamplerAdvanced
No module named 'triton'
Do you know how to fix it?
install triton.
Triton is not native for Windows, it's for Ubuntu/Linux. Use RunPod, ask chat gpt how to use it or search tutorials on YouTube.
Pip install triton-windows, I had the same issue on a different workflow
Hi,
In some of the notes in the workflow it mentions training images downloads. But I can't seem to figure out where to get those. Anyone know where to get them? It also mentions a T2V and I2V workflow that you had success with. I also can't find that
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.