celll1
Results
2
issues of
celll1
**Description:** This pull request introduces modifications to the Text Encoder to support input token lengths exceeding 75 tokens, specifically up to 3 chunks. The implementation has been confirmed to work...
# Draft PR: SageAttention This PR applies SageAttention to the Attention Processor in the model’s UNet/Transformer. By introducing **SageAttention 2.1.1**, we expect to achieve a training speed improvement of approximately...