We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Many SD checkpoints need a different VAE, either from the original SD or a custom one. Provide an option in the extras file to load and include that.
The text was updated successfully, but these errors were encountered:
feat(api): add option for custom VAE to extras file (#145)
2c66cc5
This required a small change to the VAE conversion code:
[2023-02-17 01:05:11,258] INFO: onnx_web.convert.diffusion_original: converting VAE [2023-02-17 01:05:11,264] ERROR: onnx_web.convert.diffusion_original: exception setting up output: ['Traceback (most recent call last):\n', ' File "/home/ssube/onnx-web/api/onnx_web/convert/diffusion_original.py", line 1316, in extract_checkpoint\n converted_vae_checkpoint = convert_ldm_vae_checkpoint(vae_checkpoint, vae_config)\n', ' File "/home/ssube/onnx-web/api/onnx_web/convert/diffusion_original.py", line 646, in convert_ldm_vae_checkpoint\n new_checkpoint = {"encoder.conv_in.weight": vae_state_dict["encoder.conv_in.weight"],\n', "KeyError: 'encoder.conv_in.weight'\n"] [2023-02-17 01:05:11,264] ERROR: onnx_web.convert.diffusion_original: pipeline or config is not set, unable to continue. [2023-02-17 01:05:11,410] INFO: onnx_web.convert.diffusion_original: converted original Diffusers checkpoint to Torch model
Sorry, something went wrong.
Successfully merging a pull request may close this issue.
Many SD checkpoints need a different VAE, either from the original SD or a custom one. Provide an option in the extras file to load and include that.
The text was updated successfully, but these errors were encountered: