
Based on version 2.1, the model was distilled using an 8-step distillation algorithm. It is recommended to use 8-step prediction. Compared to version 2.1, images are clearer and compositions are more reasonable when using 8-step prediction.
Based on version 2.1, the model was distilled using an 8-step distillation algorithm. It is recommended to use 8-step prediction. Compared to version 2.1, images are clearer and compositions are more reasonable when using 8-step prediction.