Vchitect / Latte

Latte: Latent Diffusion Transformer for Video Generation.
Apache License 2.0
1.69k stars 176 forks source link

Works. But question: Attributes passed, but not expected (LatteTransformer3DModel) #111

Closed MarsThunder closed 1 month ago

MarsThunder commented 2 months ago

Running quantized code for 9GB works fine. Console feedback before loading pipeline components says:
"The config attributes {'attention_type': 'default', 'double_self_attention': False, 'norm_num_groups': 32, 'num_vector_embeds': None, 'only_cross_attention': False, 'upcast_attention': False, 'use_linear_projection': False} were passed to LatteTransformer3DModel, but are not expected and will be ignored. Please verify your config.json configuration file."

I checked config.json file in .cache folder and it does indeed have many of those attributes listed. Just curious why that message was produced.

maxin-cn commented 2 months ago

The information returned by the console is an unnecessary parameter in LatteTransformer3D. We will remove redundant parameters from config.json. Thank you for your feedback.

github-actions[bot] commented 2 months ago

Hi There! 👋

This issue has been marked as stale due to inactivity for 14 days.

We would like to inquire if you still have the same problem or if it has been resolved.

If you need further assistance, please feel free to respond to this comment within the next 7 days. Otherwise, the issue will be automatically closed.

We appreciate your understanding and would like to express our gratitude for your contribution to Latte. Thank you for your support. 🙏