WAN 2.1 LoRA

Text prompt for video generation

Things you do not want to see in your video

Image to use as a starting frame for image to video generation.

The aspect ratio of the video. 16:9, 9:16, 1:1, etc.

LOADING...

The number of frames to generate (1 to 5 seconds)

LOADING...

The model to use. 1.3b is faster, but 14b is better quality. A LORA either works with 1.3b or 14b, depending on the version it was trained on.

LOADING...

The resolution of the video. 720p is not supported for 1.3b.

LOADING...

Optional: The URL of a LORA to use

Strength of the LORA applied to the model. 0.0 is no LORA.

Strength of the LORA applied to the CLIP model. 0.0 is no LORA.

Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.

LOADING...
30

Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts

160
5.0

Higher guide scale makes prompt adherence better, but can reduce variation

010
8.0

Sample shift factor

010

Set a seed for reproducibility. Random by default.

2 CREDITS

Run the workflow to see results

QUEUE

LOADING...

ACTIVE: 0QUEUED: 0

GENERATION HISTORY

LOADING...

TOTAL: 0 GENERATIONS

FLOWS

NO FLOWS
    WAN 2.1 with LoRA - Custom Style Video Generation AI | DeepFish AI - Generative AI Platform