Nerogar
[Bug]: Can't train SD1.5 - no model
What happened?
Training with 1.5 doesn't work after new install. I can't find the model directory to download and put it on there manually.
Repository Not Found for url: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/tokenizer/added_tokens.json.
Please make sure you specified the correct repo_id and repo_type.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.
FileNotFoundError: [Errno 2] No such file or directory: 'runwayml/stable-diffusion-v1-5'
What did you expect would happen?
It would work !
Relevant log output
No response
Output of pip freeze
No response
Thanks for your quick response. It still gives the same error. I ran update.bat successfully.
I think because this is a new install and the huggingface 1.5 information has been removed from their website recently, this is the cause. (Even if you click on the link in the ticket above provided by the error message, it doesn't work in the browser). Maybe there is a way to point it to an alternative source. Because this is a clean install I do not already have the files required.
true runwayml removed their repos and causing so many apps to fail that were depending on their repo :/
Correct, this is not an issue with OneTrainer. RunwayML removed their models from huggingface, they're no longer publicly available. What you're getting is an error caused by hitting a dead API endpoint.
the default runwayml/stable-diffusion-v1-5 and runwayml/stable-diffusion-inpainting repositories for SD1.5 don't exist anymore. You can still train this model if you have the checkpoint or diffusers model downloaded. Just select the downloaded model as your base model.
This means that the presets don't work anymore. But since there is no official hosted version of this model anymore, I can't fix the presets. You will need to do it manually.