copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is t
I was using the https://github.com/ashleykleynhans/runpod-worker-instantid project, and then I changed the original model wangqixun/YamerMIX_v8 to Justin-Choo/XXMix_9realisticSDXL. Then an error occurred.
show error：
"Error(s) in loading state_dict for Resampler:\n\tsize mismatch for proj_out.weight: copying a param with shape torch.Size([2048, 1280]) from checkpoint, the shape in current model is torch.Size([768, 1280]).\n\tsize mismatch for proj_out.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768]).\n\tsize mismatch for norm_out.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768]).\n\tsize mismatch for norm_out.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([768])."
GitHub
GitHub - ashleykleynhans/runpod-worker-instantid: InstantID : Zero-...
InstantID : Zero-shot Identity-Preserving Generation in Seconds | RunPod Serverless Worker - ashleykleynhans/runpod-worker-instantid
4 Replies
sounds like corupted model file
GitHub
GitHub - unrulpkk/runpod-worker-instantid: InstantID : Zero-shot Id...
InstantID : Zero-shot Identity-Preserving Generation in Seconds | RunPod Serverless Worker - unrulpkk/runpod-worker-instantid
GitHub
runpod-worker-instantid/src/download_checkpoints.py at main · unrul...
InstantID : Zero-shot Identity-Preserving Generation in Seconds | RunPod Serverless Worker - unrulpkk/runpod-worker-instantid
@Papa Madiator pipeline = fetch_pretrained_model('Justin-Choo/XXMix_9realisticSDXL', **args)