-
Notifications
You must be signed in to change notification settings - Fork 67
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
RuntimeError: Input type (c10::Half) and bias type (float) should be the same #7
Comments
What is your setting? It works on my end.
|
Seems that the decoder VAE on the refiner is somehow not fp16. Did you change any config? You can also disable refiner to see if it still happens. |
PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512 SDXL_MODEL_DIR=pretrained_models OFFLOAD_BASE=false OFFLOAD_REFINER=false python app.py
Dense Chen
***@***.***
…------------------ Original ------------------
From: "TonyLianLong/stable-diffusion-xl-demo" ***@***.***>;
Date: Fri, Aug 18, 2023 11:05 AM
***@***.***>;
Cc: "Dense ***@***.******@***.***>;
Subject: Re: [TonyLianLong/stable-diffusion-xl-demo] RuntimeError: Input type (c10::Half) and bias type (float) should be the same (Issue #7)
What is your setting? It works on my end.
To create a public link, set `share=True` in `launch()`. 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:30<00:00, 1.62it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:13<00:00, 1.15it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:23<00:00, 2.10it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:08<00:00, 1.85it/s]
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Seems like it still works if the models are not offloaded.
|
Since you loaded custom weights, it's possible that somehow fp32 weights are loaded. You probably want to check whether you have fp16 weights (https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main/vae). If you loaded fp32 weights, you can add |
I have disabled refiner via |
It seems like that. A minor modification maybe required to make this repo more robust. |
Since I could not reproduce this, could you show me your diff? |
It is ok for use to generate images for the first time. However, it will raise the following error if we generate images for second time.
The text was updated successfully, but these errors were encountered: