The generated character shots are all in slow motion.
Thank you for your work. I tried several times with the same prompt and found that, compared to the original model, the scenes showing character movements are all in slow motion after using this Lora.
Hi, thank you for your feedback. The T2V lora slows the motion down, we are currently finding a way to solve this.
The I2V lora is better than the T2V lora, still worse than the 40-step base model though.
On the native, use 3 ksamplers, with the first step at cfg 3.5 without light. On the wrapper, you need to insert a variable value on the first cfg sampler.
On the native, use 3 ksamplers, with the first step at cfg 3.5 without light. On the wrapper, you need to insert a variable value on the first cfg sampler.
A very interesting recommendation pls let me know how exactly to set up the ksamplers? 2 samplers for high noise 1st sanpler 1step cfg 3.5, 2nd sampler 2 steps with lora and 1 sampler for low....2 steps?
If this is about the new Seko lora, I have the same issue with I2V. The videos are all in slow motion. I am using native ComfyUI components together with sageattention.
3ksampler
1 ksampler cfg 3.5 no lora (1-4 steps) HIGH
2 ksampler cfg 1 (1-4 steps) ltrx x2 HIGH
3 ksampler cfg 1 (1-4 steps) ltrx 0,7 LOW
Its an issue with resolutions somehow! My test: res 1280x720 normal speed, 960x544 a bit slower. 832x480 slow motion ..even though 832x480 is 1 of the recommended resolutions.
Prompt from the creators of the loras: In a warmly lit living room, an elderly man with gray hair sits in a wooden armchair adorned with a blue cushion. He wears a gray cardigan over a white shirt, engrossed in reading a book. As he turns the pages, he subtly adjusts his posture, ensuring his glasses stay in place. He then removes his glasses, holding them in his hand, and turns his head to the right, maintaining his grip on the book. The soft glow of a bedside lamp bathes the scene, creating a calm and serene atmosphere, with gentle shadows enhancing the intimate setting.
having the same issue, everything in slow motion
That's because he has forgotten a comma. Edit nodes.py in the ComfyUI-WanVideoWrapper to add this comma back on line 4608 and it'll load.
Edited my comment to make it clearer.
by the way any workflow to test this?
by the way any workflow to test this?
It's essentially just a burn reduction algorithm. You can apply it to any existing workflow like this (works with I2V as well):
Essentially it means in the high sampler you can set CFG to 7 instead of 1 and you will get significantly less burn than if you don't use these nodes.
The author uploaded this workflow: https://github.com/user-attachments/files/22057300/2S-WVW-WAN22_T2V_A14B-v1.1.WIP.json
That's because he has forgotten a comma. Edit nodes.py in the ComfyUI-WanVideoWrapper to add this comma back on line 4608 and it'll load.
Ehhhh...?
Ctrl+F is your friend. I'm sure you can figure out where to add the comma. It's towards the end of the file if you have the right branch.
By the way the lightning euler scheduler is not in the branch and has to be checked out from the other branch. Inside ComfyUI-WanVideoWrapper\wanvideo\schedulers, run:
git checkout upstream/scheduler_test fm_solvers_euler.py
Replace __init__.py in that folder with https://pastebin.com/rf9jCjC7 and then both CFG skimming and lightning_euler will work.
Assuming you followed https://huggingface.co/lightx2v/Wan2.2-Lightning/discussions/20#68b10cc0a459d1e003fae631
3ksampler
1 ksampler cfg 3.5 no lora (1-4 steps) HIGH
2 ksampler cfg 1 (1-4 steps) ltrx x2 HIGH
3 ksampler cfg 1 (1-4 steps) ltrx 0,7 LOW
CFG 3.5 makes everything black for me :/ I need to stay at 1.0