Switches to the F1 model (different DiT path and logic).

If checked, 'Input Image (Video Start)' is hidden. Each batch item uses a random image from the folder.

Resolution Options (Choose One)

1 200
1 120
1 60
1 100
1 50
LoRA 1
0 2
LoRA 2
0 2
LoRA 3
0 2
LoRA 4
0 2
1 20
1 10
0 1
Sample Solver

Define specific prompts and starting images for different sections of the video. For the index you can input a range or a single index. A 5 second default video has 4 sections. The first section is 0 and the last is 3

--- Control Slot 1 ---

--- Control Slot 2 ---

--- Control Slot 3 ---

--- Control Slot 4 ---

Enable FP8 precision for the main Transformer model.

Requires FP8 DiT. Use scaled math (potential quality improvement).

0 39

Decode all frames at once instead of section by section.

Attention Mode

Enable TeaCache for faster generation (shits hands).

0 1