🎨 Image Generation

Stable Cascade

Efficient image generation on smaller latent space. Two-stage generation with separate guidance scales. Generates 1-4 images with improved quality and efficiency over standard diffusion models

Example Output

Prompt

"An image of a shiba inu, donning a spacesuit and helmet"

Generated Result

Generated

Input Parameters

Detailed text prompt for image generation *

An image of a shiba inu, donning a spacesuit and helmet

Negative prompt to avoid unwanted elements

ugly, deformed

First stage inference steps (4-40)

Enter first stage inference steps (4-40)

Second stage inference steps (4-24)

Enter second stage inference steps (4-24)

First stage CFG scale (0-20)

Enter first stage cfg scale (0-20)

Second stage CFG scale (0-20)

Enter second stage cfg scale (0-20)

The size of the generated image. Width and height must be between 1024 and 4096

Default

Number of images to generate (1-4)

Enter number of images to generate (1-4)

Try Now - Sign in to Use

More Image Generation Models

Wan 2.2 Text-to-Image

Wan 2.2's 14B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail

Stable Diffusion 3.5 Medium

Latest SD 3.5 with MMDiT architecture. Enhanced image quality, typography excellence, and complex prompt understanding. Improved resource efficiency with high-quality outputs. Generate 1-4 images

OpenAI GPT Image 1

A multimodal image generation model that creates high-quality images with text rendering and world knowledge.