Plug-and-Play diffusion features

For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings.

Running on CPU 🥶 This demo does not work on CPU.

Step 1 (This step will take about 5 minutes on A10G.)

Step 2 (This step will take about 1.5 minutes on A10G.)
0 50
1 100
0 100
0 1
Negative prompt schedule
Examples
Input image Prompt for translation Negative prompt