Text-to-Video
Safetensors
t2v

ComfyUI Workflow getting error with this model in the WanVideo Diffusion forcing node.

#2
by Gemneye - opened

RuntimeError: mat1 and mat2 shapes cannot be multiplied (512x768 and 4096x5120)

I am trying to make a 960x544 video, using Wan2_1-SkyReels-V2-DF-14B-540P_fp8_e4m3fn.safetensors model, wan_2.1_vae.safetensors VAE, and umt5_xxl_fp16.safetensors text encoder. Any suggestions to what the problem is?

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment