Stable Video Diffusion v1.1 - ComfyUI

In this video I share a simple workflow that will let you take Images and convert them to Video clips using SVD 1.1 (just released today). It is an improvement on previous version and much better at Portrait/Vertical images than v1.0. Check out my YT shorts for samples.

More result samples at the end of the video as well. Let me know if you have any questions, its pretty easy to use and have fun.

[jaimeortega]

This is great. Do you know if you can control the animation (still using ComfyUI)? Say, having it match a dialogue or something.

[polystormstudio]

Any chance of doing a how-to-install video? There are no instructions that I can see on the huggingface page and the instructions on the github page it links to are well over my head. I'll subscribe if you do!

[liquidmind]

hello friend, what type of COMFY are you using that shows that progress bars about CPU GPU RAM and VRAM etc. on the right side of comfy?

[KodandocomFaria]

Do you know how to finetune this model ? Perhaps a tutorial about finetuning can help the community to improve model's quality and we see more good models being released

[TopGunMan]

Did you rename lcm-lora-sdxl.safetensors? On huggingface it seems to be named (which is a terrible name).

[DEREAL-]

Is there any way to change the Home directory of Pinokio?

[RahulGupta]

lora key not loaded
lora key not loaded
lora key not loaded

ERROR shape '[640, 1024]' is invalid for input of size 1310720
ERROR shape '[640, 1024]' is invalid for input of size 1310720
ERROR shape '[640, 1024]' is invalid for input of size 1310720
ERROR shape '[640, 1024]' is invalid for input of size 1310720
ERROR shape '[1280, 1024]' is invalid for input of size 2621440

my console showing these errors, what could be the issue? I have same setup as you, same models, same lora all same.