-
-
Notifications
You must be signed in to change notification settings - Fork 1.1k
New issue
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
Inference with a pretrained model #272
Comments
^^ |
I am trying to write simple scripts with I do the code below as the params in clip = OpenAIClipAdapter("ViT-L/14")
prior_network = DiffusionPriorNetwork(
dim = 768,
depth = 12,
dim_head = 64,
heads = 12
)
diffusion_prior = DiffusionPrior(
net = prior_network,
clip = clip,
timesteps = 1000,
cond_drop_prob = 0.1
) when loading the checkpoints with I got the error below:
does anyone have some idea? |
same problem with me, i am finding solution now |
you can try set strict to false, maybe is ok |
See my response here. This may help you too. |
Hiya, is there a simple inference script that uses a specific checkpoint to load a fully trained model and generate images?
It is not clear how to use this repo without finetuning the model.
The text was updated successfully, but these errors were encountered: