Forum Replies Created
-
AuthorPosts
-
Mmm… The only things I can think of are:
- Use a T4 instance (that’s what I used)
- Remove or rename the custom_nodes folder in AI_PICS > ComfyUI
Hi David, I just tested the workflow on Colab, and it works correctly. I used the dreamshaper model and the motion model in the workflow. Did you change any settings?
Good find! I have fixed the issue.
I haven’t used it but it uses Kohya in the backend, so it should work.
Yes, I am in the process of writing the lessons. Should be up within a week.
Thanks for the review!
I’m now refreshing the comfy course and will put more advanced techniques there.
Yes: https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/blob/main/svd_xt.safetensors
I also added it to the ComfyUI notebook.
The SVD one is a bit tricky to fix. I will work on it, but you can use Comfyui in the meantime.
Is this the SVD or the ComfyUI notebook?
The extension has been updated and doesn’t work with the original models.
The lessons have been updated. In essence, download the LoRAs from the following link.
https://huggingface.co/conrevo/AnimateDiff-A1111/tree/main/lora_v2
They only work with this v2 motion model.
https://huggingface.co/conrevo/AnimateDiff-A1111/blob/main/motion_module/mm_sd15_v2.safetensors
My bad, should be working now.
Welcome Javier!
Hi, the flux sampler is there if you run the notebook with the default version. I guess you must have removed the version hash so it is using the latest version.
The flux sampler was removed yesterday. https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/2554
I now pinned the notebook to a newer version of forge but still have the flux sampler.
Hey David, it is fixed. I also added a checkbox for installing Inpaint Anything.
-
AuthorPosts