☰
Image Generation
Video Generation
Latent Image Inpainting
Audio Generation
Text to Video
Enter prompt:
Enter negative prompt:
Number of Inference Steps:
50
Guidance Scale:
7.5
Image Height:
512
Image Width:
768
Generate Image
Number of Inference Steps:
25
Guidance Scale:
7.5
Frame Rate:
7
Motion Bucket ID:
180
Noise Augmentation Strength:
0.1
Upload Image:
Generate Video
Upload Content Image:
Pick a style
Enter prompt:
Kadinsky Embedding Strength:
0.7
Number of Inference Steps:
50
Guidance Scale:
7.5
Image Height:
512
Image Width:
768
Upload Image:
Generated text will appear here.
Generate Image
Enter prompt:
Choose an image with a person to change background:
Replace Scene
Enter Audio Prompt:
Duration (seconds):
Steps:
CFG Scale:
Generate Audio
Text Prompt:
Generate Text2Video