WAN 5B Text-to-Image
Efficient high-resolution photorealistic image generation with powerful prompt understanding and artistic flexibility.
The text prompt to guide image generation.
The size of the generated image.
Negative prompt for video generation.
Number of inference steps for sampling. Higher values give better quality but take longer.
If set to true, input data will be checked for safety before processing.
Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.
Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality.
Shift value for the image. Must be between 1.0 and 10.0.
Random seed for reproducibility. If None, a random seed is chosen.
