narrowsnap

Thanks for your codes which work very well. The origin DQN(1.dqn.ipynb) set batch_size=32 which is ineffective on GUP so I changed it to 256. But it's bad performance. Is there...

Separate inference 720p video with 24G VRAM

9

## Add VAE encoder for reference. Reduce inference VRAM by separate process: 1. Run text_encoder and save text embeding. 2. Run VAE encoder if reference_path in prompt.(optional) 3. Run STDiT...